Open AccessSTAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition
Author(s) -
Wei Liu,
Chaofeng Chen,
Kenneth K. Wong,
Zhizhong Su,
Junyu Han
Publication year - 2016
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.30.43
Subject(s) - computer science , star (game theory) , artificial intelligence , net (polyhedron) , pattern recognition (psychology) , computer vision , astrophysics , physics , mathematics , geometry
In this paper, we present a novel SpaTial Attention Residue Network (STAR-Net) for recognising scene texts. The overall architecture of our STAR-Net is illustrated in fig. 1. Our STARNet emphasises the importance of representative image-based feature extraction from text regions by the spatial attention mechanism and the residue learning strategy. It is by far the deepest neural network proposed for scene text recognition.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom