How does Textract deal with actual text in a PDF?

0

How does Textract deal with PDF documents that contain actual text, as in text that you can copy and paste into a Notepad document (as opposed to an image that Textract can recognise text in). Does Textract simply take the text verbatim, or does it render the text as an image, and then OCR it?

主题

机器学习和人工智能

标签

Amazon Textract

语言

English

已提问 2 年前325 查看次数

1 回答

最新
投票最多
评论最多

1

已接受的回答

Textract does the latter where it first renders the PDF as an image and then performs OCR on it.

AWS-User-7817432

已回答 2 年前

专家

已审核 9 个月前

相关内容

AWS Textract 人工审核流程，pdf图片加载失败
专家
rePost Polyglot
已提问 7 个月前
Textract S3 权限问题
专家
rePost Polyglot
已提问 7 个月前
The ciphertext refers to a customer master key that does not exist, does not exist in this region, or you are not allowed to access (Query Id: b2c74c7e-21ed-4375-8712-cd1579eab9a7)
专家
rePost Polyglot
已提问 5 个月前
Rekognition使用detect_text 无法找到明显的文本。
专家
rePost Polyglot
已提问 7 个月前
为什么我尝试加入组织时，会收到错误：“You can only join an organization whose Seller of Record is same as your account”？
AWS 官方已更新 2 年前
如何通过 API Gateway 将图片或 PDF 文件上传到 Amazon S3？
AWS 官方已更新 1 年前
为什么我的 CloudFormation 堆栈停滞在 IN_PROGRESS 状态？
AWS 官方已更新 1 年前
我从 Amazon S3 桶下载或复制对象时，为什么会出现错误“The ciphertext refers to a customer master key that does not exist, does not exist in this region, or you are not allowed to access”（加密文字指的是不存在、此区域不存在或者您无权访问的客户主密钥）？
AWS 官方已更新 1 年前