Single Shot Text Detector with Regional Attention

This project modify tensorflow object detection api code to predict oriented bounding boxes. It can be used for scene text detection.

This is a c++ project deploying a deep scene text reading pipeline with tensorflow. It reads text from natural scene images. It uses frozen tensorflow graphs. The detector detect scene text locations. The recognizer reads word from each detected bounding box.

Script identification in natural scene image and video frames using an attention based Convolutional-LSTM network (Pattern Recognition, 2019)

A Word Spotting Method in Scene Images based on Character Recognition

A novel region proposal network for more general object detection ( including scene text detection ).

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection (TIP 2019)

Pytorch implementation for pixel-wise scene text segmentation based on DeepLabV3+

A curated list of papers and resources for scene text detection and recognition

Geometric Augmentation for Text Image

This repository provides train＆test code, dataset, det.&rec. annotation, evaluation script, annotation tool, and ranking.

Code for generating synthetic text images in Indic languages. Based on Ankush et al. CVPR'16.

Convolutional recurrent neural network for scene text recognition or OCR in Keras

ASTER in Pytorch

The code of "Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting"

Implementation of EAST scene text detector in Keras

Recognizing cropped text in natural images.

Making machine learning and computer vision simple.

Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.

TextBoxes++: A Single-Shot Oriented Scene Text Detector