Textract是如何识别PDF中的文本的？

0

【以下的问题经过翻译处理】请问Textract是如何识别PDF中的文本的？就是那种可以直接贴到记事本中的纯文本。 Textract是直接使用PDF中包含的文本，还是先把PDF当成图片，然后通过OCR识别的？

Topics

Machine Learning & AI

Tags

Amazon Textract

Language

中文 (简体)

EXPERT

rePost Polyglot

asked 9 months ago35 views

1 Answer

Newest
Most votes
Most comments

Are these answers helpful? Upvote the correct answer to help the community benefit from your knowledge.

0

【以下的回答经过翻译处理】后者。先当成图片，然后OCR识别。

EXPERT

rePost Polyglot

answered 9 months ago

Relevant content

如何讓 IAM 使用者只看的到自己建立的資源 ( How to allow IAM users to only see resources they have created.)
Accepted Answer
kerokero
asked 2 months ago
S3上无法使用Chunked上传文件｜ Unable to use Chunked to upload files on S3
rePost-User-1798329
asked a year ago
我通过Elastic Beanstalk创建环境之后，用code pipeline关联github中的springcloud项目deploy失败了，下面是具体报错原因
rePost-User-1988868
asked a year ago
使用finalshell 链接老是中断或无法链接
rePost-User-9459845
asked a year ago
How do I download an invoice for my monthly AWS charges?
AWS OFFICIALUpdated a year ago
How do I upload an image or PDF file to Amazon S3 through API Gateway?
AWS OFFICIALUpdated a year ago
How do I change billing information on the PDF version of the AWS invoice that I receive by email?
AWS OFFICIALUpdated 3 months ago
How do I update the mailing address associated with my AWS account?
AWS OFFICIALUpdated 2 years ago
A Brief Primer for Applying Deep Graph Learning to Molecular Graphs
EXPERT
Joshua_B
published 2 years ago
Modernize .NET workloads on AWS
EXPERT
Gayathri Krishnamoorthy
published a year ago