Tesseract OCR vs scanR vs Amazon Rekognition Comparison | StackShare | StackShare

Amazon Rekognition vs Tesseract OCR vs scanR

Overview

Tesseract OCR

Stacks95

Followers286

Votes7

GitHub Stars70.7K

Forks10.4K

scanR

Stacks2

Followers44

Votes0

Amazon Rekognition

Stacks80

Followers152

Votes4

Advice on Tesseract OCR, scanR, Amazon Rekognition

Vladyslav

Sr. Directory of Technology at Shelf

Oct 25, 2019

Decided

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.

53.3k views53.3k

Comments

Detailed Comparison

Tesseract OCR	scanR	Amazon Rekognition
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.	scanR is a simple OCR API service that supports 32 languages and can extract text from images or PDF files.	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.
-	Real time image to text - post us your image and get a response with the text inside.; No need to manage servers or infrastructure, simply call our API and get the text inside any image.;	-
Statistics
GitHub Stars 70.7K	GitHub Stars -	GitHub Stars -
GitHub Forks 10.4K	GitHub Forks -	GitHub Forks -
Stacks 95	Stacks 2	Stacks 80
Followers 286	Followers 44	Followers 152
Votes 7	Votes 0	Votes 4
Pros & Cons
Pros 5 Building training set is easy 2 Very lightweight library Cons 1 Works best with white background and black text	No community feedback yet	Pros 4 Integrate easily with AWS Cons 1 AWS

What are some alternatives to Tesseract OCR, scanR, Amazon Rekognition?

Google Cloud Vision API

Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API.

Tesseract.js

This library supports over 60 languages, automatic text orientation and script detection, a simple interface for reading paragraph, word, and character bounding boxes. Tesseract.js can run either in a browser and on a server with NodeJS.

libpng

It is the official Portable Network Graphics (PNG) reference library. It is a platform-independent library that contains C functions for handling PNG images. It supports almost all of PNG's features, is extensible, and has been widely used and tested.

OpenJPEG

It is an open-source JPEG 2000 codec written in C language.

ZXing

It is a barcode scanning library for Java, Android. Decode a 1D or 2D barcode from an image on the web.

EasyOCR

It is ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai.

libjpeg

It is a free library for JPEG image compression.

Restb.ai

It tags, classifies, and organizes your real estate images.

Basilica

An API that embeds high-dimensional data like images and text. You send an image, and you back a vector of floats.

MMOCR

It is an open-source toolbox based on PyTorch and mmdetection for text detection, text recognition, and the corresponding downstream tasks including key information extraction.