Need advice about which tool to choose?Ask the StackShare community!
Amazon Rekognition vs Tesseract OCR: What are the differences?
What is Amazon Rekognition? Image Detection and Recognition Powered by Deep Learning. Amazon Rekognition is a service that makes it easy to add image analysis to your applications. With Rekognition, you can detect objects, scenes, and faces in images. You can also search and compare faces. Rekognition’s API enables you to quickly add sophisticated deep learning-based visual search and image classification to your applications.
What is Tesseract OCR? Tesseract Open Source OCR Engine. Tesseract was originally developed at Hewlett-Packard Laboratories Bristol and at Hewlett-Packard Co, Greeley Colorado between 1985 and 1994, with some more changes made in 1996 to port to Windows, and some C++izing in 1998. In 2005 Tesseract was open sourced by HP. Since 2006 it is developed by Google.
Amazon Rekognition and Tesseract OCR can be categorized as "Image Analysis API" tools.
Tesseract OCR is an open source tool with 28.1K GitHub stars and 5.38K GitHub forks. Here's a link to Tesseract OCR's open source repository on GitHub.
According to the StackShare community, Tesseract OCR has a broader approval, being mentioned in 6 company stacks & 6 developers stacks; compared to Amazon Rekognition, which is listed in 7 company stacks and 4 developer stacks.
AWS Rekognition has an OCR feature but can recognize only up to 50 words per image, which is a deal-breaker for us. (see my tweet).
Also, we discovered fantastic speed and quality improvements in the 4.x versions of Tesseract. Meanwhile, the quality of AWS Rekognition's OCR remains to be mediocre in comparison.
We run Tesseract serverlessly in AWS Lambda via aws-lambda-tesseract library that we made open-source.
Pros of Amazon Rekognition
- Integrate easily with AWS4
Pros of Tesseract OCR
- Building training set is easy5
- Very lightweight library2
Sign up to add or upvote prosMake informed product decisions
Cons of Amazon Rekognition
- AWS1
Cons of Tesseract OCR
- Works best with white background and black text1