Search

Your search keyword '"Cunzhao Shi"' showing total 99 results
Start Over Author "Cunzhao Shi"
99 results on '"Cunzhao Shi"'

1. Scene text recognition by learning co‐occurrence of strokes based on spatiality embedded dictionary

Author

Song Gao, Chunheng Wang, Baihua Xiao, Cunzhao Shi, Wen Zhou, and Zhong Zhang

Subjects
scene text recognition, high-level image understanding, text information, scene images, local strokes, spatiality embedded dictionary, Computer applications to medicine. Medical informatics, R858-859.7, Computer software, QA76.75-76.765
Abstract

Text information contained in scene images is very helpful for high‐level image understanding. In this study, the authors propose to learn co‐occurrence of local strokes for scene text recognition by using a spatiality embedded dictionary (SED). Unlike spatial pyramid partitioning images into grids to incorporate spatial information, the authors SED associates every codeword with a particular response region and introduces more precise spatial information for robust character recognition. After localised soft coding and max pooling of the first layer, a sparse dictionary is learned to model co‐occurrence of several local strokes, which further improves classification performance. Experimental results on two scene character recognition datasets ICDAR2003 and CHARS74 K demonstrate that their character recognition method outperforms state‐of‐the‐art methods. Besides, competitive word recognition results are also reported for four benchmark word recognition datasets ICDAR2003, ICDAR2011, ICDAR2013 and street view text when combining their character recognition method with a conditional random field language model.

Published
2015
Full Text
View/download PDF

42. Unconstrained end-to-end text reading with feature rectification

Author

Cunzhao Shi, Baihua Xiao, Yanna Wang, Chen Du, and Chunheng Wang

Subjects
Computer science, business.industry, Feature extraction, Perspective (graphical), Pattern recognition, Text reading, 02 engineering and technology, Text recognition, 01 natural sciences, Convolutional neural network, End-to-end principle, Rectification, Artificial Intelligence, Feature (computer vision), 0103 physical sciences, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, 010306 general physics, business, Software
Abstract

We propose an end-to-end trainable network that can simultaneously localize and recognize irregular text from images. Specifically, we find the feature incompatibility problem, which arises from the contradiction between detection and recognition tasks for feature extraction of the convolutional neural network, and propose to introduce the larger-scale features for the recognition part to improve the accuracy of recognition instead of using the same feature with the detection. To extract effective text features for perspective and curved text recognition, we propose a position-sensitive network to rectify the text proposal features in the recognition branch. The position-sensitive network, which is trained in a weak supervision way, takes the proposal detection feature as input and outputs the feature rectification information. Experiments demonstrate that the proposed method can achieve state-of-the-art or highly competitive performance compared with baselines on a number of benchmarks.

Published
2021

50. Adversarial learning based attentional scene text recognizer

Author

Baihua Xiao, Jingzhong Jiang, Yanna Wang, Chunheng Wang, Jinyuan Zhao, and Cunzhao Shi

Subjects
business.industry, Computer science, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, 02 engineering and technology, 01 natural sciences, Image (mathematics), Adversarial system, Rectification, Artificial Intelligence, 0103 physical sciences, Signal Processing, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Learning based, Computer vision, Computer Vision and Pattern Recognition, Artificial intelligence, Image rectification, 010306 general physics, business, Generative adversarial network, Software
Abstract

In this paper, we propose an adversarial learning based attentional scene text recognizer to solve the distortion problem of scene text image. We choose a rectification module which can rectify images in both horizontal and vertical directions, and use a recognizer based on the attention mechanism. Through the adversarial learning of the rectification network and the recognition network, we iteratively improve the rectification effect and the recognition performance. The entire network is trained with weak supervision, so only images and corresponding text labels are needed. Our method achieves high performance for both regular and irregular scene text images, and the experimental results tested on multiple benchmarks prove that our method achieves the performance of state-of-the-art.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results