TextProposals

Implementation of the method proposed in the papers " TextProposals: a Text-specific Selective Search Algorithm for Word Spotting in the Wild" and "Object Proposals for Text Extraction in the Wild" (Gomez & Karatzas), 2016 and 2015 respectively.

TextTopicNet

Self-supervised learning of visual features through embedding images into text topic spaces

text_extraction

This code is the implementation of the method proposed in the paper “Multi-script text extraction from natural scenes” (Gomez & Karatzas) to appear in ICDAR2013 conference.

single-shot-str

Single Shot Scene Text Retrieval, ECCV 2018. L. Gomez*, A. Mafla*, M. Rusiñol, D. Karatzas.

erfilter_train

ufl_scene_text_recognition

C++ (OpenCV) implementation of the Unsupervised Feature Learning algorithm of Adam Coates and Andrew Ng for Scene Text Detection and Recognition

script_identification

ConTextTransformer

er_ocr_tesseract

Scene text recognition baseline using the Tesseract API.

DCText

Text Detection by DCT energy localization

ST-VQA_Loc

Multimodal grid features and cell pointers for Scene Text Visual Question Answering

DAS2016_Tutorial1

Slides and sample code demos for DAS2016 Tutorial 1