Search Results for author: Shuye Zhang

Found 5 papers, 1 papers with code

DeepText: A Unified Framework for Text Proposal Generation and Text Detection in Natural Images

5 code implementations24 May 2016 Zhuoyao Zhong, Lianwen Jin, Shuye Zhang, Ziyong Feng

In this paper, we develop a novel unified framework called DeepText for text region proposal generation and text detection in natural images via a fully convolutional neural network (CNN).

Region Proposal Text Classification +1

Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition

no code implementations18 Apr 2016 Zecheng Xie, Zenghui Sun, Lianwen Jin, Ziyong Feng, Shuye Zhang

This paper proposes an end-to-end framework, namely fully convolutional recurrent network (FCRN) for handwritten Chinese text recognition (HCTR).

Handwriting Recognition Handwritten Chinese Text Recognition +1

Character Proposal Network for Robust Text Extraction

no code implementations13 Feb 2016 Shuye Zhang, Mude Lin, Tianshui Chen, Lianwen Jin, Liang Lin

Maximally stable extremal regions (MSER), which is a popular method to generate character proposals/candidates, has shown superior performance in scene text detection.

Scene Text Detection Text Detection

Recognition Confidence Analysis of Handwritten Chinese Character with CNN

no code implementations25 May 2015 Meijun He, Shuye Zhang, Huiyun Mao, Lianwen Jin

In this paper, we present an effective method to analyze the recognition confidence of handwritten Chinese character, based on the softmax regression score of a high performance convolutional neural networks (CNN).

regression

Cannot find the paper you are looking for? You can Submit a new open access paper.