文本边缘检测文献调研

edge detection issue on Text detection in images

Structured Edge Detection Toolbox
https://github.com/pdollar/edges

A collection of edge/contour/boundary detection papers and toolbox.
https://github.com/MarkMoHR/Awesome-Edge-Detection-Papers

Implementation of “ROBUST TEXT DETECTION IN NATURAL IMAGES WITH EDGE-ENHANCED MAXIMALLY STABLE EXTREMAL REGIONS” By Huizhong Chen, Sam S. Tsai, Georg Schroth, David M. Chen, Radek Grzeszczuk and Bernd Girod
https://github.com/akab/TextDetection

Edge App for pose estimation, car color and type detection, as well as text detection.
https://github.com/AloshkaD/intel_edge_detection_segmentation_pose

This is part of the project. The goal is to process the image, using edge detection, grayscale image, noise reduction, layout analysis to split the text into each single character
https://github.com/yunjuanwang/OCR-character-detection

Converted characters in images to text utilizing a Hopfield neural net and canny edge detection (OpenCV). Summer project (2015) at the M3 Lab at University of Michigan, Ann Arbor.
https://github.com/chaipedada/M3-OCR

Extracted text from images and real time video by performing preprocessing steps like gray scaling, noise removal, thresholding, dilation, erosion, rescaling, deskewing, canny edge detection, template matching and added bounding boxes for all the characters.
https://github.com/Vineethreddyc11/OCR-in-Python-with-OpenCV-Tesseract-and-Pytesseract

LiveEdgeDetection is an Android document detection library built on top of OpenCV. It scans documents from camera live mode and allows you to adjust crop using the detected 4 edges and performs perspective transformation of the cropped image. It works best with a dark background.
https://github.com/adityaarora1/LiveEdgeDetection

It’s is an Android document detection library built on top of OpenCV 4.6.0 It works best with a dark background.
https://github.com/hannesa2/LiveEdgeDetection

Edge-based method for text detection from complex document images
https://ieeexplore.ieee.org/abstract/document/953800