Text Understanding in Visual Data

Text recognition (traditionally called OCR) is crucial for visual understanding and reasoning in many application scenarios.

We focus on Arbitrary-Shaped Text detection and Recognition and related Natual Language Processing tasks for understanding these text.

MMOCR: A comprehensive toolbox for text detection, recognition and understanding, openmmlab, ocr 

Text Detection

Fourier contour embedding for arbitrary-shaped text detection, sensetime, ocr 
Geometry normalization networks for accurate scene text detection, rotated detection, oriented detection, sensetime, ocr 
Speeding up scene text detection, Guided CNN, Fast Scene Text Detector, sensetime, ocr 

Text Recognition

ICDAR2019-ArT Arbitrary-Shaped Scene text recognition, sensetime, ocr 
RobustScanner: Dynamically enhancing positional clues for robust text recognition, sensetime, ocr 

profile counter Stats

Copyright © 2023 Wayne Zhang