Questions tagged with Amazon Rekognition

We have been testing the celebrity recognition service and have noticed one issue when we upload the picture of a famous Indian actor, Salman Khan. The last name that comes up in the response is actually an abusive word of local language in India. You can test it for yourself by uploading the following image. https://www.bollywoodhungama.com/wp-content/uploads/2021/10/salman-khan.jpg How the response can be fixed, if at all?

Facing issue - AWS FACE RECANTATION not detecting many faces from video. Wr are loosing many expected faces from video. In our application we are using AWS face recognition services to detect faces from video. Earlier(4 months back) it is working fine and was able to detect many faces but now the recognised faces count is very less. We are losing many faces that we can see are present in video by naked eye. Service should be able to detect those faces. So my question is, **Is their any changes in service or is their any restriction added to the service? ** we are using these services: 1. start_face_detection (To Start video processing at amazon end) 2. get_face_detection (To Get detected faces )

Actually Rekognition works fine but when I use a filename containing a colon (:) for the S3Object, it makes an error. It is very problematic for me because all my files already have colons and I can't change their names. So if use this It works fine: ``` { "Image":{ "S3Object":{ "Bucket":"console-sample-images", "Name":"skateboard.jpg" } ``` but if i use a name with a colon like this It gives me an error. ``` { "Image":{ "S3Object":{ "Bucket":"console-sample-images", "Name":"skate:board.jpg" } ``` Error output: `{"name":"Error","content":"{\"__type\":\"InvalidS3ObjectException\",\"Code\":\"InvalidS3ObjectException\",\"Message\":\"Unable to get object metadata from S3. Check object key, region and/or access permissions.\"}","message":"faultCode:Server.Error.Request faultString:'null' faultDetail:'null'","rootCause":{"errorID":2032,"target":{"bytesLoaded":174,"dataFormat":"text","bytesTotal":174,"data":"{\"__type\":\"InvalidS3ObjectException\",\"Code\":\"InvalidS3ObjectException\",\"Message\":\"Unable to get object metadata from S3. Check object key, region and/or access permissions.\"}"},"text":"Error #2032: Stream Error. URL: https://rekognition.eu-west-1.amazonaws.com","currentTarget":{"bytesLoaded":174,"dataFormat":"text","bytesTotal":174,"data":"{\"__type\":\"InvalidS3ObjectException\",\"Code\":\"InvalidS3ObjectException\",\"Message\":\"Unable to get object metadata from S3. Check object key, region and/or access permissions.\"}"},"type":"ioError","bubbles":false,"eventPhase":2,"cancelable":false},"errorID":0,"faultCode":"Server.Error.Request","faultDetail":null,"faultString":""}` Is there a workaround for this problem? (encoding the ':' a certain way?) Thank you for your help.

Hi everyone! Currently, I've accomplished detecting all the faces from a collection and then generating sub-galleries of each individual subject with all their photos associated with the ruby SDK '~> 1.65' In order to do this, I've indexed the faces of all photos within a collection, list all the faces (https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/Rekognition/Client.html#list_faces-instance_method), then grabbing each face_id recognized and search the faces related to that face_id (https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/Rekognition/Client.html#search_faces-instance_method), and delete the face id used to do the API call and all the returned ones to tell when a new detected subject starts and ends. My issue is that some indexed faces are returning a wrong bound box not fitting the face properly with a few images, sometimes not even close to the face (I've seen a brick as a bound box). This is weird because internally those "wrong faces" seem to be associated properly with other faces as if the service were just returning wrong box values but doing all the AI jobs properly. Is there a way to prevent or tweak the call params to prevent this? or is it normal for the API to return sometimes wrong values due to the multiple decimals? Thanks in advance!

Hi everyone! Currently, I've accomplished detecting all the faces from a collection and then generating sub-galleries of each subject with all their photos associated with the ruby SDK '~> 1.65' To do this, I've indexed the faces of all photos within a collection, list all the faces (https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/Rekognition/Client.html#list_faces-instance_method), then grabbing each face_id recognized and search the faces related to that face_id (https://docs.aws.amazon.com/sdk-for-ruby/v3/api/Aws/Rekognition/Client.html#search_faces-instance_method), and delete the face id used to do the API call and all the returned ones to tell when a new detected subject starts and ends. My issue is that the search faces API returns different results depending on which face id param you are doing the request with. For example, if there are 10 faces ids detected that belong to a person (1, 2, 3, ..., 10), the search faces call with face id = 1 param, should return the faces id (2, 3, 4, ..., 10) but if you continue to do this with the other face ids this is not always the case with some scenarios where the search faces call with face id = 3 has returned a subset of the previously mentioned like just (4, 5, 6). Is there any other way to achieve this to prevent this kind of "error"? if not, this is a real concern for us because it depends on the order in which we call the search faces with different face ids, and sometimes it seems like there is more than 1 subject detected with almost the same photos when in reality it's the same person. Thanks in advance!

When submitting a video to Rekognition, get_text_detection is always returning Timestamp with seconds precision instead of milliseconds. For example: ``` text_detection: {'Timestamp': 4000, 'TextDetection': {'DetectedText': 'ITV Lunchtime News', 'Type': 'LINE', 'Id': 0, 'Confidence': 99.68327331542969, 'Geometry': {'BoundingBox': {'Width': 0.1505126953125, 'Height': 0.033203125, 'Left': 0.35760498046875, 'Top': 0.0947265625}, 'Polygon': [{'X': 0.35760498046875, 'Y': 0.0947265625}, {'X': 0.50811767578125, 'Y': 0.0947265625}, {'X': 0.50811767578125, 'Y': 0.1279296875}, {'X': 0.35760498046875, 'Y': 0.1279296875}]}}} ``` Code snippets: ``` response = self.rekognition.start_text_detection( Video=self.param_video, NotificationChannel=self.param_channel, JobTag=self.job_tag, Filters=self.param_filters, ) self.job_id = response["JobId"] ``` ``` while not finished: response = self.rekognition.get_text_detection( JobId=self.job_id, MaxResults=max_results, NextToken=pagination_token ) for text_detection in response["TextDetections"]: print(f'text_detection: {text_detection}') if "NextToken" in response: pagination_token = response["NextToken"] else: finished = True ``` Looks like a bug to me. But it's weird that I didn't find anyone reporting it before. So am I doing something wrong?

We discovered an issue on Moderation's classes in Amazon Rekognition while scanning a lot of social network content. A lot of selfies are tagged as Sexual Content / Activity or Nudity with a very high confidence score (97-99%). The pictures are not ambiguous, for instance it happens a lot on selfies with Moisturizing face mask (example: https://i.pinimg.com/736x/bd/bd/0f/bdbd0f00a8b661c3e5a7b5cf7fa5023f.jpg). But it happens too on random pictures, for instance a group of young girls taking a picture at a train station. Do you have any insights about that? It would help us a lot.

Hi all, Just wondering if there is ever a need to re-index photos added to a Rekognition collection? My company is used to working with other 3rd party facial recognition vendors and any time a new algorithm version is released, we need to re-enroll/re-index the existing photos in order to use it. Obviously when you need to pay a fee for each indexing API call, this would amount to a lot of extra costs if so. Also, how does AWS Rekognition handle algorithm upgrades? Is it automatic/transparent or do you have to approve the use of new algorithm changes? Thanks!

Hi, New to Rekognition and just had some resiliency related questions that I'm struggling to find the answers for. 1. How are the underlying photos in a collection stored? Does AWS store these in an S3 bucket? If so, is there any need to store the source photos in your own private S3 bucket or is simply having them in a collection sufficient? 2. How are Rekognition collections backed up? Thanks!

Hi there, I am not understanding how Rekognition deals with multiple images for the same face, I need help! Scenario: - I have 3 years worth of school classroom photos and need to create yearbook of 5 of the students - I need to identify which photos have only the 5 students in them, and ignore all others. To enhance the accuracy, I was reading the [documentation](https://docs.aws.amazon.com/rekognition/latest/dg/recommendations-facial-input-images.html) that recommends to use multiple images of the same face when using IndexFaces. > When creating a collection using IndexFaces, use multiple face images of an individual with different pitches and yaws (within the recommended range of angles). We recommend that at least five images of the person are indexed—straight on, face turned left with a yaw of 45 degrees or less, face turned right with a yaw of 45 degrees or less, face tilted down with a pitch of 30 degrees or less, and face tilted up with a pitch of 45 degrees or less I think I get this by default as I will be indexing all images, which will contain many many images of the students, from all angles. This is correct, no? Or do I need to do something specific to tie the photos of the same student to the one FaceId? I noted that if I use 5 images of the same person, using IndexFaces, I get 5 different FaceIds returned. I thought (perhaps incorrectly) that Rekognition would recognise that it's the same face and just update it's internal data about the FaceId, and return the same FaceId for each of the subsequent 4 images (after the first one is indexed) that are of the same face. So, can anyone help me: 1. Should indexing multiple images of the same person result in multiple FaceIds? 2. Internally, does Rekognition group all those FaceIds together, so it does not matter which FaceId I use in the future to search on - it will still benefit from the multiple images I uploaded for that face? 3. Is there any difference in performance if I search by `SearchFaces` or by `SearchFacesByImage` 4. Is my approach of indexing all the images I have, then searching on a single known FaceId a the student the way to go? sorry for multiple questions :) hope you can help, hive mind!

While trying to create an dataset in Amazon Rekognition by importing images from S3 I get "manifest_has_too_many_rows" error when I try to import more than 7 folders of images

I am having a HTML textarea where a user enters a descriptive text. I want to know which service to use (consume) to detect if the user-inputted text is toxic or not. rekognition/content-moderation and comprehend seem to be detecting data from media sources like images, videos or PDFs.

Are there any plans to have AWS Rekognition tested by NIST? That's a requirement when selecting facial recognition algorithms for many contracts in my company. Thanks!

I'm having trouble finding any detailed performance specs on AWS Rekognition. Would anybody be able to point me in that direction? I've seen some metrics thrown around such as 1.5 second search time when using the SearchFaces API, but it doesn't state how many photos that search was against. I'm looking to design something fairly large that will have approximately 100 million indexed photos in a collection. That collection will be compared against by approximately 25,000 new photos every day. Basically I'm just looking to determine how this algorithm compares against some non-cloud algorithms (ie. Cognitec, Neurotech, etc.) Thanks!

Hi all, If I've previously indexed a collection of say 100 million photos using the IndexFaces API and I want to run a one to many search against that entire collection of indexed photos for every new applicant that comes in to my system, would I just need to run a single SearchFaces API call? Or would I need to run 100 million SearchFaces or CompareFaces API calls? I'm just trying to estimate the pricing on using Rekognition in a facial recognition system and this answer obviously plays a massive factor in the pricing. Thanks!

Amazon Rekognition Model metrics are available for only test dataset, not train dataset. I think having access to training results ,not only testing results, can be of immense use to everyone using Rekognition. Even if we do not know or are unable to change model architecture(AWS internal team is responsible for this), one very simple but useful information to be gained from comparing train and test results could be( if the train F1 score > test score by a lot) ascertaining whether train and test distributions are vastly different or not. Of course many other things can also be inferred from this information. Hence, I sincerely believe gaining access to this sort of train metrics information will be useful to everyone and enhance user experience. Can anyone here associated with AWS internal team/working inform me why this is not a feature.

I tried several license plates of different states of US. The results are very inconsistent. Sometimes all the words even are not recognised. I have a use case to extract only the license plate numbers of all states of US from image as text. Are we already working on such requirement?

I am running the specific example "KinesisVideoRekognitionIntegrationExampleTest" from https://github.com/aws/amazon-kinesis-video-streams-parser-library to produce a local "output" to display the bounding box results from amazon rekognition with reference to this set of steps: https://aws.amazon.com/blogs/machine-learning/easily-perform-facial-analysis-on-live-feeds-by-creating-a-serverless-video-analytics-environment-with-amazon-rekognition-video-and-amazon-kinesis-video-streams/ My video is fed properly to KVS ( able to be seen playing on web console) However i am getting this error when running the junit test with nothing displayed on jframe `Running rekognition-kds-stream-application to process stream RekognitionVideoBlog-Stream as worker host.docker.internal:9d3a6f88-50a1-4ab6-8b65-93594b7627ad...14:09:28.173 [pool-2-thread-2] ERROR com.amazonaws.kinesisvideo.parser.examples.GetMediaWorker - Failure in GetMediaWorker for streamName LiveRekognitionVideoAnalysisBlog java.lang.Error: Unresolved compilation problems: 6 The default case is already defined` The log4j is also triggering `java.lang.ClassNotFoundException: com.amazonaws.services.lambda.runtime.log4j.LambdaAppender `

Am testing the docker/rtsp example as provided by: https://docs.aws.amazon.com/kinesisvideostreams/latest/dg/examples-gstreamer-plugin.html how do i edit the "region" such that it targets the KVS i have created in eu-west-1 rather than the default "us-west-2" when running the docker image

Based on the amazon doc mentioned here about custom labelling and how rekognition trains, https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/tm-debugging-json-line-errors.html#tm-warning-WARNING_UNANNOTATED_RECORD, it seems as if training on images with intentionally unassigned bounding boxes does not happen. I want to know why that's the case. From my humble understanding of standard ML object detection models, we ought to include information from images containing at least 1 label/bounding box and also those images with no labels at all (the model needs information about those data/data representations with negative feedback / nothing to label at all). Can anyone please shed light on why Amazon rekognition chooses to train on images with atleast 1 bounding box and ignores (as in not used in training /computing loss) the human curated images with intentionally no bounding boxes ? Thanks!

We have detected a small issue with moderation labels, We are running some images through the rekognition service, We tested it with some images of guns, we have found that close up images of guns does not trigger the moderation labels response. It will only trigger when we lower the minimum confidence to less than 4, which is unfortunately too low for us to run in production. One of the images we have been using is hosted on S3 and can be found at: https://dl-demo.s3.eu-west-2.amazonaws.com/messages/message_87.jpg Can AWS Include such images in their training sets?

I am getting a Provisioned Rate exceeded error when calling the DeleteFaces api of AWS rekognition, using the current version of the .net DSK. I think what triggered the error in the first place is that I was running some batches in parallel, and even though they don't make many calls to AWS rekognition, it happened occasionally that their calls were simultaneous, exceding the limit of 5 per seconds (I managed retry attempts but I had not realised the SDK had its own retry policy by default). However it seems now that any single call I make to DeleteFaces returns a "Provisioned Rate exceeded" exception, no matter how long I wait before I retry (>1h), or how many face ids I try to delete per call (50 to 4096), or the retry policy of the sdk (legacy or standard). Other functions of the rekognition API seem to work fine. Is there a rate limit other than the 5 calls per seconds advertised as a default for rekognition (and when that limit is reached, how long does it take before it allows new calls)? Or is it some sort of shadow ban after a certain number of provisioned rate exceeded errors (and if so how long should I wait before the ban is lifted)? Does it matter how many faces I delete in one call? I already batch faceids by batches of 4096. Do these get further split by the .net sdk in multiple calls, resulting in some sort of api calls amplification?

I am doing this on dekstop. I have created a dataset with training and testing, added all my labels to the images etc. Here is the error I am getting. "Amazon Rekognition Custom Labels couldn't train your model. Check that your IAM policy and your S3 bucket policy are correct. For more information, see the Amazon Rekognition Developer Guide." I have been searching the forums, tried creating a policy but I still cannot figure out the issue. Even a point in the right direction would be very awesome. I am very new to AWS and this is project I have to do for class. Thanks!

I have requested for a video segmentation using rekognition tool. The documentation says that the output of the "sqs.receive_message" should be like this: Response Syntax { 'Messages': [ { 'MessageId': 'string', 'ReceiptHandle': 'string', 'MD5OfBody': 'string', 'Body': 'string', 'Attributes': { 'string': 'string' }, 'MD5OfMessageAttributes': 'string', 'MessageAttributes': { 'string': { 'StringValue': 'string', 'BinaryValue': b'bytes', 'StringListValues': [ 'string', ], 'BinaryListValues': [ b'bytes', ], 'DataType': 'string' } } }, ] } But I don't receive such a response. Here is what I always get: {'ResponseMetadata': {'RequestId': 'xxxxxx', 'HTTPStatusCode': 200, 'HTTPHeaders': {'x-amzn-requestid': 'xxxxxx', 'date': 'Thu, 27 Jan 2022 11:32:58 GMT', 'content-type': 'text/xml', 'content-length': '240'}, 'RetryAttempts': 0}} Any idea where the problem is?

Hello, I have tried to train an Amazon Rekognition (custom label) object detection model on a set of labeled medical images to detect medical tools. I have about 23,000 labeled images with 8 classes. I have tried training the model 2 times, but both times I am getting a "training failed" message after almost 24 hours of training: "Amazon Rekognition experienced a service issue." How can I solve this? Is there any reason this error is occurring? The model seemed to successfully train when I used a smaller subset of the data with only about 1500 labeled images. Is the dataset size the issue? Any help would be appreciated! Thank you.

I want to train a model using these pictures as training data: https://www.dropbox.com/s/n35jne68hjws2d4/runes.zip?dl=0 And the test data will be this: https://imgur.com/4LQIUSX.jpg And this: https://imgur.com/LOKzEOp.jpg I have succeeded in labeling everything I need and my understanding is that this should be viable (or does anybody have any feedback on how my data should look like for this to work? Maybe I'm doing something wrong?) However I've tried to train my Rekognition model five times and it's failed every time with "Amazon Rekognition experienced a service issue. It seems to me that this is an internal failure in the service, can I get some feedback on what I can do?

The `MaxLabels` argument works on the Amazon Rekognition Image but not using a Video. I have this PHP payload I use: ``` 'ClientRequestToken' => (string)Str::uuid(), 'JobTag' => VideoOperations::REKOGNITION_LABEL_DETECTION, 'NotificationChannel' => [ 'RoleArn' => config('rekognition.notification_channel.role_arn'), 'SNSTopicArn' => config('rekognition.notification_channel.sns_arn'), ], 'MinConfidence' => config('rekognition.min_confidence'), 'MaxLabels' => config('rekognition.max_labels'), 'Video' => [ 'S3Object' => [ 'Bucket' => config('rekognition.bucket'), 'Name' => $video->filename ], ] ``` I checked the official github AWSDocs Rekognition samples and could not find an implementation of the `MaxLabels` on a Video Rekognition. Is it not supported? https://github.com/awsdocs/amazon-rekognition-developer-guide/search?q=MaxLabels

Cheers! I am using Rekognition to detect text in a picture. At one point I have to detect whether text has a line over it or not. By line, I mean whether text is crossed out (like in supermarket catalogues when you have an original price crossed out and the discounted price not crossed out). Is something like that possible with Rekognition? Thanks!

Hi, I wanted to know if there is any plan for Rekognition to be tested with NIST in the near future? I've tested top 5 NIST evaluated algorithms and Rekognition blows them out of the water. Having NIST scores would be huge for us end users.

I receive the following error when training a model with Custom labels with a small dataset (around 500 images): Model Status: "TRAINING_FAILED" Status Message: "Amazon Rekognition experienced a service issue." I have received this error 6 times ranging in the past 3 days. The training process runs for a few hours failing. Any help will be appreciated on this issue. Thanks

Hello, In the quotas and guidelines for Rekognition, it is mentioned that "Amazon Rekognition Video supports a maximum of 20 concurrent jobs per account". This number is too less for my use case. Is there any way it can be increased by raising a request? In case there cannot be more than 20 concurrent jobs, are the other jobs stored in some sort of internal queue or are they lost?

Hi, We have been using AWS Rekognition for searching faces in our collection. However, today (27/01/2022) we observed that the faces which earlier matched with a certain similarity are not being matched from today. Has there been a recent update to the face matching model? Also, the matches and similarity which I am getting from search faces function, when I try matching them with compare faces I get a different similarity. Looking forward to understand what's the issue here. Regards, Swarup

I am using Custom Labels to see if the model can recognize which quail laid a certain egg. When I examine the project, I see that the correct option didn't have the highest confidence, but was still listed as the model getting the correct result from the egg. Why is this happening???

Hi, I'm currently learning on AWS Rekognition. I am quite interested in the AWS Rekognition SDK, especially the Face Comparison. Is there any diagram flow regarding this service? From what I understand, the Face Comparison is done on the cloud because when doing the comparison I need to upload the image. Is the image that I upload saved on temp storage or not? And is it possible to do it without uploading the image so all the process is done on-premise? Thank you

I would like to perform content moderation from AWS Rekognition on a Kinesis Video Stream real time. I see there is documentation for using AWS Rekognition to detect faces on Live Kinesis Video Stream but is it possible to call the contentmoderation method function and perform the same task. If yes, where will the results be stored? Also, if yes, can we extract just that part of the video where the content has been detected and store it in S3 bucket?

When dataset is created and shown in the rekognition interface. We opt to make few changes to the labels height and width. Now, before we start to train it. We need to download the manifest/json file which will have the changes that we made on the interface. The issue is that we cannot locate where the manifest file is on s3 where these changes get saved. The initial manifest used to generate the dataset while creating the project does not contain any updates to the records. (on which we made changes)

I want to build an app that will recognize what emojis have been used on the wallpaper. So for instance this app will receive an input image like [this](https://i.stack.imgur.com/5wRQm.png) And on output should return an array of names of recognized emojis: ``` [ "Smiling Face with Sunglasses", "Grinning Face with Smiling Eyes", "Kissing Face with Closed Eyes" ] ``` Of course, the names of these emojis will come from the names of files of training images. For example, [this](https://i.stack.imgur.com/BaEGG.png) file, will be called `Grinning_Face_with_Smiling_Eyes.jpg` I would like to use `AWS Rekognition Label`, but they require a minimum of 10 images of each emoji for training. As you know, I can only provide one image of each emoji, because there is no more option, they are in 2D ;) Now my question is: What should I do? How can I skip these requirements? Which service should I choose? On the stack, I have read that I should for instance rotate each image 12 times by 30o, or crop the emoji by half. I have done that, but, precision is very small - around `0.3` PS. In real business instead of emojis, there are covers of the books, which AI has to recognize. There is also one image per book-cover photo in 2D.

I have the need to use "text in image" from Amazon Rekognition to process more than 300k images per month. Does Amazon Rekognition provide a way to process images in batch, doing only 1 request to analyze multiple images at once? And the main question: does a batch process is cheaper than a single process? For example, I have 10 images to extract the text using Amazon Rekognition. The cost for 10 requests to Rekognition (one for each image) is the same as the cost for 1 batch request sending 10 images at once?

I am trying to implement an Multi-label Image classification model in AWS Rekognition. I used manifest file to create the dataset in AWS Rekognition, but the Rekognition console cannot take the dataset from s3 bucket. while creating the dataset, the console has following errors: 1. Amazon Rekognition custom labels cannot get the dataset entries. Try refreshing the console. 2. The manifest file contains too many invalid rows. I have created the manifest file using the link: https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/md-create-manifest-file-classification.html I followed the steps as described in the following link to create the dataset in AWS Rekognition: https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/md-create-manifest-file.html#create-dataset-procedure-manifest-file The s3 bucket has two folders 1. Train - storing my training images 2. Manifestfiles - storing the manifest file Any help will be appreciated.

Hi, We have separate accounts for dev, stage and production and I'm wondering if it's possible to copy labeled dataset which was created on dev account to stage and production accounts? Thanks.

Hello There is a **very old bug** (first reported on this forum in 2017 and again in 2018) that throws error **Invalid Parameter Exception** when **CompareFaces** is called with input JPEG file to search for a given face and the output/search JPEG does not have any faces on it. In other words - the Input Image (S3 object) does have a Face to look for and the Output JPEG photo to compare does not have any face on it or not any recognizable face (such as person is facing backwards, for example) or output image JPEG has a photo of a bottle or large object which obscures the Input face. So it just throws Invalid Parameter Exception which is 100% wrong. This is akin to throwing invalid parameter error when End Of File is found on Read - which is not error but an expected condition of reading a file. This bug that makes Rekognition **too slow to use and unproductive** because the error is bogus. We are required to make 2 API calls (costing both time and money) to first detect any face on output JPG file and only then call compare-face if any face is found by a detect method. Why? Compare Face call should simply return 0.0 confidence output with API success if there is no face on the output search JPEG, it should not return spurious errors because this condition is not error, the no-face-found is a perfectly acceptable result. When will this bug be fixed?? I have tried using Rekognition today (9 Nov 2021) and still getting Invalid Parameter Exception error. thank you.

Hi, I am doing Content moderation of videos and some category of videos do not return accurate labels. So I tried using Custom Labels in Rekognition. I did not see any way to do that, it was just available for images. Is that right? Is there any other way to custom train videos? Thank you

Hello, I used the NodeJS AWS SDK v3 to create Face Detection Jobs on AWS Recognition. I created a bunch of jobs a week ago. Now when I try to fetch the faces found in the job, I am getting a JobId ResourceNotFoundException. What I tried before posting this post : - I made sure that the JobId is correct - I tried every region of AWS My feeling is that jobs expire over time. Is this a thing ? Or are job available for ever ? I hope some of you had the same problems :)

Hi, The AWS Rekognition Service has a limit of 30 Bounding boxs per Image When use Detect Custom Labels Action? I have tried to change the MaxResults parameter to other value (50) but i still getting the Maximum of 30 My custom Labeled detected on every Image that i use. And it's supposed the Rekognition Model detect more than 30 in the images that i'm using. At first i though the model needs more training to detect more my custom label. But this happen to every image i use, so i'm starting thinking if this is a Limit. I'm using confidence = 1%. Regards, Fábio Santos

Hi' im' trying to setup a training dataset for object localization using the manifest method. Im' getting the following error: **401: The S3 input manifest file s3://custom-labels-console-us-east-1-833b01ea2f/datasets/TestTrainingSet/manifests/output/output.manifest does not have the correct JSON format.** I couldn't figure out what's wrong with the json, was hoping somebody could help me resolving the issue. Following is the json for one of image files. {"source-ref": "s3://custom-labels-console-us-east-1-833b01ea2f/DentalCEPH/TrainingData/001.png", "bounding-box": {"image_size": \[{"width": 1935, "height": 2400, "depth": 3}], "annotations": \[{"class_id": 0, "top": 929, "left": 768, "width": 128, "height": 128}, {"class_id": 1, "top": 968, "left": 1405, "width": 128, "height": 128}]}, "bounding-box-metadata": {"objects": \[{"confidence": 1}, {"confidence": 1}], "class-map": {"0": "sella turcica", "1": "nasion", "2": "orbitale", "3": "porion", "4": "subspinale", "5": "supramentale", "6": "pogonion", "7": "menton", "8": "gnathion", "9": "gonion", "10": "lower incisal incision", "11": "upper incisal incision", "12": "upper lip", "13": "lower lip", "14": "subnasale", "15": "soft tissue pogonion", "16": "posterior nasal spine", "17": "anterior nasal spine", "18": "articulate"}, "type": "groundtruth/object-detection", "human-annotated": "yes", "creation-date": "2020-11-18T02:53:27", "job-name": "custom labels"}} Thank you, V.Vamsi Krishna Edited by: vkrishna on Mar 7, 2021 3:53 AM

If a person that Amazon Rekognition Video recognizes leaves the camera frame and then comes back into the frame, does Amazon Rekognition recognize them as the same person?

Hello, For a model that has two different classes, rust and scratches, and there happened to be a rusty scratch, would it confuse the model to annotate the same spot with both classes? Let me know if you need more clarification. I appreciate the thoughts! Matt

Is the full hierarchy/ontology of object and scene labels used in Rekognition available for reference anywhere? I know I can piece it together through the payloads received back from Rekognition, but that's much more time consuming and prone to errors due to the absence of some labels in my images. Thanks! Nadav Edited by: naquent on Nov 13, 2020 6:51 AM

I want to build a camera that automatically recognizes a specific pet with image or video recognition. What AWS service can I use to identify an individual pet (not just the pet type). I've tried to use AWS Rekognition, but it can only differentiate between animal types, race, or color. Amazon SageMaker could be another option to create a completely new mode, but is very costly. What other AWS services can I use to identify specific pets?

After **successfully** creating a **custom label model** on the **console**, I am trying to use the model for prediction as follows: from boto3 import client rekog = client('rekognition') response = rekog.detect_custom_labels(Image={'S3Object':{'Bucket':bucket, 'Name':key}}, ProjectVersionArn=project_version_arn) But I am getting the following Exception error: <br><br> An error occurred **(ResourceNotReadyException)** when calling the DetectCustomLabels operation: ProjectVersion arn:aws:rekognition: us-east-1:blah-blab-blal------ **is not ready** I thought the ProjectVersion should be ready once the the model is created with a defined and available **project_version_arn**. It is more **than one day** now and it still saying **not ready**. Is there anything I have to do to make the model **(project_version_arn)** ready?

Hi guys, I was playing with Jobs, FaceSearch and FaceDetection while I realized that even though they are run against the same video in S3 they return different values for the same finding. For instance bot Jobs run against the same bucket object and i get difference in BoundingBox and Landmarks which i think should be the same and also Iremember that while i tested this 4 months ago i got those expected results. Example: Video with just 1 Person. - aws rekognition start-face-detection --video "S3Object={Bucket=facejobs,Name=head-pose-face-detection-female.mp4 }" - aws rekognition start-face-search --video "S3Object={Bucket=facejobs,Name=head-pose-face-detection-female.mp4 }" --collection-id test-collection Getting the results: aws rekognition get-face-detection --job-id "3661ab79c711bbd530ca5a910003d..." aws rekognition get-face-search --job-id "cc3555290d2093bec860519bf53403e8..." Comparing: FaceDetection Results ------------------------- ```json { "JobStatus": "SUCCEEDED", "VideoMetadata": { "Codec": "h264", "DurationMillis": 134584, "Format": "QuickTime / MOV", "FrameRate": 12.0, "FrameHeight": 432, "FrameWidth": 768 }, "Faces": \[ { "Timestamp": 0, "Face": { "BoundingBox": { "Width": 0.13135695457458496, "Height": 0.36436259746551514, "Left": 0.4154500961303711, "Top": 0.22901538014411926 }, "Landmarks": \[ { "Type": "eyeLeft", "X": 0.4518287479877472, "Y": 0.3687707185745239 }, { "Type": "eyeRight", "X": 0.5152483582496643, "Y": 0.3756844997406006 }, { "Type": "mouthLeft", "X": 0.451990008354187, "Y": 0.5045619010925293 }, { "Type": "mouthRight", "X": 0.5046293139457703, "Y": 0.5103421807289124 }, { "Type": "nose", "X": 0.47848179936408997, "Y": 0.4353737533092499 } ], "Pose": { "Roll": 2.838758707046509, "Yaw": -1.3927381038665771, "Pitch": 10.166311264038086 }, "Quality": { "Brightness": 79.76757049560547, "Sharpness": 26.1773681640625 }, "Confidence": 99.99970245361328 } }, { "Timestamp": 499, ``` FaceSearch -------------------- ```json { "JobStatus": "SUCCEEDED", "VideoMetadata": { "Codec": "h264", "DurationMillis": 134584, "Format": "QuickTime / MOV", "FrameRate": 12.0, "FrameHeight": 432, "FrameWidth": 768 }, "Persons": \[ { "Timestamp": 0, "Person": { "Index": 0, "Face": { "BoundingBox": { "Width": 0.13410408794879913, "Height": 0.365193247795105, "Left": 0.4145432412624359, "Top": 0.2288028597831726 }, "Landmarks": \[ { "Type": "eyeLeft", "X": 0.4514598548412323, "Y": 0.3685579001903534 }, { "Type": "eyeRight", "X": 0.5149661898612976, "Y": 0.37557920813560486 }, { "Type": "mouthLeft", "X": 0.4519285261631012, "Y": 0.5038205981254578 }, { "Type": "mouthRight", "X": 0.5038713216781616, "Y": 0.5095799565315247 }, { "Type": "nose", "X": 0.47897493839263916, "Y": 0.43512672185897827 } ], "Pose": { "Roll": 1.5608868598937988, "Yaw": -18.46771240234375, "Pitch": 8.22950553894043 }, "Quality": { "Brightness": 81.00172424316406, "Sharpness": 53.330047607421875 }, "Confidence": 99.99984741210938 } }, "FaceMatches": \[] }, { "Timestamp": 499, ``` So basically it makes using both calls to get insights impossible. Think the situation when you want to detect emotions and also search a face. And what is weirder, which i can not confirm as it was 3 months ago is that i tested this and the results where the same.. I even saved the json from that time but i can not be certain the way that i got them as i don't remember my implementation, or if i manipulate them :( But i got this: FaceDetection ---------------- ```json { "JobStatus": "SUCCEEDED", "VideoMetadata": { "Codec": "h264", "DurationMillis": 1500, "Format": "QuickTime / MOV", "FrameRate": 30, "FrameHeight": 720, "FrameWidth": 1280 }, "Faces": \[{ "Timestamp": 499, "Face": { "BoundingBox": { "Width": 0.16875895857810974, "Height": 0.4913144111633301, "Left": 0.4124282896518707, "Top": 0.2672847807407379 ``` FaceSearch --------------- ```json { "JobStatus": "SUCCEEDED", "VideoMetadata": { "Codec": "h264", "DurationMillis": 1500, "Format": "QuickTime / MOV", "FrameRate": 30, "FrameHeight": 720, "FrameWidth": 1280 }, "Persons": \[{ "Timestamp": 499, "Person": { "Index": 0, "Face": { "BoundingBox": { "Width": 0.16875895857810974, "Height": 0.4913144111633301, "Left": 0.4124282896518707, "Top": 0.2672847807407379 }, "Landmarks": \[{ ``` As you can see, BoundingBox are equal on both APIs jobs. Thanks for any insight you can provide me. Again, the use case is to be able to use Emotions with Search API as the latter does not return Emotions. Also weird choice.

Is it possible to use Amazon Rekognition to detect faces of employees in a video of my company employees? I know Amazon Rekognition Video Analysis can analyze videos and detects objects, activities, people, celebrities, but can I use it for custom people (e.g. company employee) detection? In this case, instead of a celebrity name, it will be an employee name.

I setup a user in sagemaker. Added role permissions. Executed python code snippet to create collection. An error occurred (AccessDeniedException) when calling the CreateCollection operation: User: arn:aws:sts::767317008127:assumed-role/AmazonSageMaker-ExecutionRole-20200713T124931/SageMaker is not authorized to perform: rekognition:CreateCollection on resource: arn:aws:rekognition:us-east-1:767317008127:collection/test ive tried To add role policy to user Recreate user in sagemaker Im able to create s3 bucket through portal under user id need some help getting unstuck.

Can Rekognition be used to find out where a face is looking (which direction the eyes are pointed to)? What about being able to tell only one eye is present in an image (someones face is turned to the side)? Edited by: AGMarasco on Jun 24, 2020 12:22 PM

Hello! Is it possible to delete images that have been uploaded to a custom labels dataset? If I delete all label annotations from an image will it be removed from training or will it still be used in the training process? Thanks for the help! Matt

I have followed the tutorial in <https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/cp-create-project.html>. - In the console, I am unable to see, as mentionned, the points 2, 3 and 4: 2. In the left pane, choose Use Custom Labels. The Amazon Rekognition Custom Labels landing page is shown. 3. Choose Get started. 4. Choose Create Project. - In the cli, I am able to make a call to the API and have a prediction on an image in my bucket. But if I try `aws rekognition create-project --project-name my-project`, I get an error "An error occurred (AccessDeniedException) when calling the CreateProject operation". I have tried with both root user and a newly created user with permissions "AmazonRekognitionFullAccess" and "AdministratorAccess" and my credentials are set as well. I used "aws configure" and correctly passed my access key, secret key and region. I checked it in "~/.aws/credentials" and "~/.aws/config". Don't know what I am missing here, any help would be appreciate.

Hi, Thank you for your time to read my question. I want to use Video Streaming (from Webcam) to detect face and other attributes like (Emotion, Landmarks, Pose, Smile, EyeOpen, MouthOpen). I can get the results from a video stored in S3 bucket by using GetFaceDetection API. Now, I want to analyse face using Video Streaming (from Webcam). I found documentation about Face Recognition: https://docs.aws.amazon.com/rekognition/latest/dg/recognize-faces-in-a-video-stream.html The sample code is written in Java. Unfortunately, I am not familiar with Java. I am looking for a sample code in Python. I summarize my question here: 1. Does Video Streaming only work with Face Recognition? 2. I don't have "Index Faces". But, can I still get Face Detection results (Bounding Box, Emotion, Pose, etc). I don't need "Face Similarity" results. 3. Is there any sample code for Python? 4. The sample code is about "Creating & Starting Streaming Video Analysis". What about the next step: "Reading Analysis Results". Is there any sample code? I am new in this field. And I didn't understand the whole process yet. I really appreciate it, if you could answer my question in a simple manner. Thanks.

Hello, My question is about Head Pose in AWS Rekognition. What is the unit of Yaw, Pitch, Roll (degree or radian)? and what is their range? And also, are they from the camera&#39;s point of view? For example, if the value of Yaw is -10, what is the rotation direction (right, left)? And is it relative to camera or frame? Thank you. Mohammad Head Pose (unit of Yaw, Pitch, Roll) (Point of View)?

Hello, I was testing Amazon Rekognition Demo. My purpose is emotion recognition. When I upload an image file, I can see the emotion as below: "appears to be happy , 99.5 %" But, what I am looking for is the probability or value of all motions (i.e. happiness, sadness, anger, etc). Even thought the probability or value of emotion is very low or zero. Is there any way to get such results? I checked other cloud services and companies for emotion recognition. They give probabilities of all their tracked emotions. If the answer is Yes, please let me know if I can get all emotion probabilities for a video. By this way, I can draw a continuous graph of emotions. I assume that summation of all probabilities must be 1 (100%). Thank you for your time. Mohammad

Hi, I am looking for a way to create datasets using manifest or auto labeling feature or any other way to allow me to label multiple objects in an image so that each object I select has a label. Tried to create datasets using manifest so that the manifest only has class_id and class-map attributes but not having any boundingbox attributes. I was able to create such datasets. From the dataset GUI, I can see each each image has multiple labels associated. However training fails with error "The manifest file contains too many invalid data objects." I made another attempt by putting same image that has multiple objects in multiple folders that represent their labels. I was able to create datasets and even successfully trained that dataset-pair. But from viewing the test result, no single image correctly labeled twice. Do you support my scenario? thank you.

What types of PPE detection does Amazon Rekognition support?

I have tried to train a model for several days now, but after a couple of hours it always fails with: "Amazon Rekognition experienced a service issue." Not much of an error message. I have trained several version before with no problems and made only minor changes in the dataset with for the latest model. What can I do to fix this?

Hello, From https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/cd-create-dataset.html I see that I can create a manifest without using SageMaker, as long as it conforms to the format specified here: https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/cd-required-fields.html But that Custom Labels Guide only shows that I can supply/specify my manifest by clicking on "Import image Labeled by SageMaker Ground Truth" Is there a way to create or modify dataset and supply my manifest programmatically? Thanks. Edited by: mymingle on Mar 2, 2020 5:48 PM

Rekognition Video label detection detects both "Person" and "Human". What is the difference or relationship between the two?

Hi Is there a way to create a dataset with custom label images programmatically? I have a large number of images which have already been labeled so I don't want to do this again via the console. All of the tutorials and demos use the console. I can't fin Any help appreciated Thanks Edited by: chunt on Dec 30, 2019 5:14 AM

Hi, I am detecting images using a custom label model and the .net api, but it is really slow. The images are hosted at S3 and and about 150KB in size. Each call takes about 3 seconds to complete. Is this normal? What could be affecting the speed? Thanks, Tomas

Hello all, I'm trying to detect custom labels and have gone through all the steps in the guide including training, labeling, starting the project etc. The problem I'm having is when I try to actually detect custom labels from AWS CLI, the following error message is encountered: ``` An error occurred (ValidationException) when calling the DetectCustomLabels operation: 1 validation error detected: Value 'arn:aws:s3:::<my bucket ARN>' at 'image.s3Object.bucket' failed to satisfy constraint: Member must satisfy regular expression pattern: [0-9A-Za-z\.\-_]* ``` According to the docs link:<https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/detecting-custom-labels.html#w1141aac36c23c10b2b1>, here is the command. ``` aws rekognition detect-custom-labels --project-version-arn "model_arn"\ --image '{"S3Object":{"Bucket":"bucket","Name":"image"}}'\ --min-confidence 70 ``` Accordingly: ``` "model_arn": copy-pasted from my model info page "bucket": copy-pasted the full S3 ARN from my S3 bucket "image": copy-pasted the full path of the image to analyze in the same S3 bucket ``` Would appreciate any suggestions into how to resolve this. Thanks.

Hi everyone, I am working with AWS Rekognition for video analysis of person tracking. I have successfully gathered all the bounding box data as well as the facial landmarks data per frame. So what I have done is grab the frame at a given timestamp and apply the bounding boxes and landmarks to the frame. However, when stitching the video back together I noticed the bounding boxes and facial landmarks flicker between frames. I am pretty sure this is due to the fact that not every frame in the video has data populated for bounding boxes and facial landmarks. Is there any solution to make the bounding boxes and landmarks not flicker when stitching the video back together. Any assistance is greatly appreciated. Thanks in advance. I have attached a video of the current issues I am encountering for explanation's sake. Edited by: brussell152 on Nov 13, 2019 10:29 AM Edited by: brussell152 on Nov 13, 2019 10:39 AM

Hey everyone, I am trying to draw bounding boxes on the frames given by the timestamp from get_label_detection. Basically after analyzing a video and calling get_label_detection I am returned a dictionary in which a key is 'Timestamp'. What I want to do is get the frame of the video at this timestamp and draw the associated bounding boxes to this frame before stitching the video back together. I am using cv2.CAP_PROP_POS_MSEC to retrieve the milliseconds for each frame but these values do not align with the output of get_label_detection 'Timestamp'. If anyone could point me in the right direction I would greatly appreciate it. Thanks in advance. Edited by: brussell152 on Oct 25, 2019 8:53 PM

I have recently followed a tutorial to create facial Rekognition app. I have the ARN resources connected for the database and rekognition, I have created the collection point making sure the IAM has the permissions to access the services it needs. The Rekognition column appears in the Dynamo DB & when I upload a photo with both enroll and verify lambda functions appear to connect. The image file format is correct(.png) but the database is showing no faces in the database with the code attached. What could the possible remaining issue be?

In my test, it seems Amazon Rekognition detects First Lady Melania Trump, but doesn't detect President Trump. I can reproduce it with aws cli: Steps to Reproduce: President Trump: $ curl -o trump.jpg https://www.whitehouse.gov/wp-content/uploads/2017/11/President-Trump-Official-Portrait-200x200.jpg $ aws rekognition recognize-celebrities --image-bytes fileb://trump.jpg --query "CelebrityFaces\[].Name" \[] First Lady Melania Trump: $ curl -o flotus.png https://www.whitehouse.gov/wp-content/uploads/2017/11/flotus-200x200.png $ aws rekognition recognize-celebrities --image-bytes fileb://flotus.png --query "CelebrityFaces\[].Name" \[ "Melania Trump" ] What could be the cause of this problem? I would appreciate if you could suggest possible solutions.

Hi , I am trying to add the faces to the collection var params = { CollectionId: "aws:rekognition:us-east-1:xxxx:collection/collectionidnewbatch", DetectionAttributes: \[ ], ExternalImageId: "testphotoid", Image: { S3Object: { Bucket: "parentbucket/nested/bucket", Name: "ab1" } } }; rekognition.indexFaces(params, function(err, data) { if (err) console.log(err, err.stack); // an error occurred else console.log(data); }); and getting following error "image.s3Object.bucket' failed to satisfy constraint: Member must satisfy regular expression pattern: \[0-9A-Za-z\.\-_]

Hello guys, I've integrated my app with Amazon Rekognition last year but now I'm getting this exception. I've updated my project with the latest version of the AWSSDK.Rekognition nuget package but it didn't solve it. Here is the code: ``` public async Task<CompareFacesResponse> CompareAsync(byte[] photo1, byte[] photo2) { var client = new AmazonRekognitionClient(awsAccessKeyId, awsSecretAccessKey, Amazon.RegionEndpoint.EUWest1); return await client.CompareFacesAsync(new CompareFacesRequest { SimilarityThreshold = 80.0f, SourceImage = new Image { Bytes = new MemoryStream(photo1) }, TargetImage = new Image { Bytes = new MemoryStream(photo2) } }); } ``` Then I got this exception: ``` Amazon.Rekognition.AmazonRekognitionException: Missing Authentication Token ---> Amazon.Runtime.Internal.HttpErrorResponseException: Exception of type 'Amazon.Runtime.Internal.HttpErrorResponseException' was thrown. at Amazon.Runtime.HttpWebRequestMessage.GetResponseAsync(CancellationToken cancellationToken) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\_mobile\HttpRequestMessageFactory.cs:line 539 at Amazon.Runtime.Internal.HttpHandler`1.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\HttpHandler.cs:line 175 at Amazon.Runtime.Internal.Unmarshaller.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.ErrorHandler.InvokeAsync[T](IExecutionContext executionContext) --- End of inner exception stack trace --- at Amazon.Runtime.Internal.HttpErrorResponseExceptionHandler.HandleException(IExecutionContext executionContext, HttpErrorResponseException exception) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\HttpErrorResponseExceptionHandler.cs:line 60 at Amazon.Runtime.Internal.ErrorHandler.ProcessException(IExecutionContext executionContext, Exception exception) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\ErrorHandler.cs:line 212 at Amazon.Runtime.Internal.ErrorHandler.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\ErrorHandler.cs:line 104 at Amazon.Runtime.Internal.CallbackHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.EndpointDiscoveryHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.EndpointDiscoveryHandler.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\Handlers\EndpointDiscoveryHandler.cs:line 79 at Amazon.Runtime.Internal.CredentialsRetriever.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\Handlers\CredentialsRetriever.cs:line 98 at Amazon.Runtime.Internal.RetryHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.RetryHandler.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\RetryHandler\RetryHandler.cs:line 137 at Amazon.Runtime.Internal.CallbackHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.CallbackHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.ErrorCallbackHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.MetricsHandler.InvokeAsync[T](IExecutionContext executionContext) at Test.Main.CompareAsync(Byte[] photo1, Byte[] photo2)... ``` **UPDATE** After enabling the logs I could find more details below... which raises a question: Is the latest nuget package compatible with .NET Core? Because I'm running this code in a Mac and I plan to deploy it in a docker container. ``` UserCrypto 1|2019-03-18T16:33:47.043Z|INFO|UserCrypto is not supported. This may be due to use of a non-Windows operating system or Windows Nano Server, or the current user account may not have its profile loaded. Unable to load shared library 'Crypt32.dll' or one of its dependencies. In order to help diagnose loading problems, consider setting the DYLD_PRINT_LIBRARIES environment variable: dlopen(libCrypt32.dll, 1): image not found AmazonRekognitionClient 2|2019-03-18T16:33:47.820Z|ERROR|An exception of type HttpErrorResponseException was handled in ErrorHandler. --> Amazon.Runtime.Internal.HttpErrorResponseException: Exception of type 'Amazon.Runtime.Internal.HttpErrorResponseException' was thrown. at Amazon.Runtime.HttpWebRequestMessage.GetResponseAsync(CancellationToken cancellationToken) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\_mobile\HttpRequestMessageFactory.cs:line 539 at Amazon.Runtime.Internal.HttpHandler`1.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\HttpHandler.cs:line 175 at Amazon.Runtime.Internal.Unmarshaller.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.ErrorHandler.InvokeAsync[T](IExecutionContext executionContext) AmazonRekognitionClient 3|2019-03-18T16:33:47.875Z|ERROR|AmazonRekognitionException making request CompareFacesRequest to https://rekognition.eu-west-1.amazonaws.com/. Attempt 1. --> Amazon.Rekognition.AmazonRekognitionException: Missing Authentication Token ---> Amazon.Runtime.Internal.HttpErrorResponseException: Exception of type 'Amazon.Runtime.Internal.HttpErrorResponseException' was thrown. at Amazon.Runtime.HttpWebRequestMessage.GetResponseAsync(CancellationToken cancellationToken) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\_mobile\HttpRequestMessageFactory.cs:line 539 at Amazon.Runtime.Internal.HttpHandler`1.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\HttpHandler\HttpHandler.cs:line 175 at Amazon.Runtime.Internal.Unmarshaller.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.ErrorHandler.InvokeAsync[T](IExecutionContext executionContext) --- End of inner exception stack trace --- at Amazon.Runtime.Internal.HttpErrorResponseExceptionHandler.HandleException(IExecutionContext executionContext, HttpErrorResponseException exception) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\HttpErrorResponseExceptionHandler.cs:line 60 at Amazon.Runtime.Internal.ErrorHandler.ProcessException(IExecutionContext executionContext, Exception exception) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\ErrorHandler.cs:line 212 at Amazon.Runtime.Internal.ErrorHandler.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\ErrorHandler\ErrorHandler.cs:line 104 at Amazon.Runtime.Internal.CallbackHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.EndpointDiscoveryHandler.InvokeAsync[T](IExecutionContext executionContext) at Amazon.Runtime.Internal.EndpointDiscoveryHandler.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\Handlers\EndpointDiscoveryHandler.cs:line 79 at Amazon.Runtime.Internal.CredentialsRetriever.InvokeAsync[T](IExecutionContext executionContext) in D:\JenkinsWorkspaces\trebuchet-stage-release\AWSDotNetPublic\sdk\src\Core\Amazon.Runtime\Pipeline\Handlers\CredentialsRetriever.cs:line 98 at Amazon.Runtime.Internal.RetryHandler.InvokeAsync[T](IExecutionContext executionContext) ``` Edited by: cleytonT on Mar 18, 2019 8:35 AM

Hi, I'm using detectLabels on an Id Card and it only returns Label Names and Confidence. The documentation says that it also returns Instances and Parents, with the bounding box of the label. I use the same image in the demo page and it returns all the info, but not when I call the API method. Could you help me please? I tested it with many images. Regards