You have to train an AI with the same material it'll be used to classify, not something close. In this case you need to train it with "emoji on wallpaper" not just "emoji"
So you'll need a library of images that you'd normally classify with the AI, that a human has manually classified, and use those to train it.
Rotation is a good start, but you might want to go for more robust transformations and a more robust model based on fine-tuning. It really depends on what you plan to feed it later - how much variability there will be in the images you expect to do inference on.
This blog talks about transfer learning / fine-tuning and could be helpful. https://aws.amazon.com/blogs/machine-learning/run-image-classification-with-amazon-sagemaker-jumpstart/
Then take a look at the methods described here for data augmentation: https://www.tensorflow.org/tutorials/images/data_augmentation
AWS Device Farm can not get the correct app activity for Android app to launch app using Appiumasked a year ago
Certificate used by Elastic Load Balancers in an unrecognized AWS account?Accepted Answerasked 4 months ago
Build a Cloud Sync App like DropBox/OneDrive for Windows to Sync S3 Dataasked 4 months ago
AI used for recognizing emojis on wallpaperasked a year ago
Environment variables for a Node app running on an EC2 Instanceasked a year ago
An beanstalk app that works fine until recentlyasked 7 months ago
Please add support for .app and .ai TLDsasked 7 months ago
What's an AWS Practice exams used for?asked a year ago
Storing/representing a hierarchical tree used for navigation within an Amplify web app and AppSync GraphQL API layer.asked 7 months ago