HsiehYiChia/Scene-text-recognition
Scene text detection and recognition based on Extremal Region(ER)
This tool helps you automatically find and read text embedded in images or video footage, even in busy or uncontrolled environments. You provide images, a folder of images, or a video stream, and it outputs the detected text. This is designed for professionals who need to extract information from visual media, such as researchers analyzing public signage, or operations teams monitoring equipment labels.
167 stars. No commits in the last 6 months.
Use this if you need to quickly extract text from a large collection of images or a live video feed, especially when the text is part of a complex visual scene.
Not ideal if you need extremely high accuracy for document scanning, as its focus is on real-world scene text rather than clean documents, or if you prefer a cloud-based API.
Stars
167
Forks
55
Language
C++
License
MIT
Category
Last pushed
May 11, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/HsiehYiChia/Scene-text-recognition"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huoyijie/AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on...
argman/EAST
A tensorflow implementation of EAST text detector
HusseinYoussef/Arabic-OCR
OCR system for Arabic language that converts images of typed text to machine-encoded text.
rtr46/meikiocr
high-speed, high-accuracy, local ocr for japanese video games
SachaIZADI/Seven-Segment-OCR
Computer vision project to automatically recognize digits characters in a seven-segments display