logo
banner

Journals & Publications

Journals Publications Papers

Papers

A Cascaded Method for Text Detection in Natural Scene Images
Jul 24, 2017Author:
PrintText Size A A

Title: A Cascaded Method for Text Detection in Natural Scene Images

 Authors: Zheng, Y; Li, Q; Liu, J; Liu, HP; Li, G; Zhang, SW

 Author Full Names: Zheng, Yang; Li, Qing; Liu, Jie; Liu, Heping; Li, Gen; Zhang, Shuwu

 Source: NEUROCOMPUTING, 238 307-315; 10.1016/j.neucom.2017.01.066 MAY 17 2017

 Language: English

 Abstract: In this paper, a novel image operator is proposed to detect and locate text in scene images. To achieve a high recall of character detection, extremal regions are detected as character candidates. Two classifiers are trained to identify characters, and a recursive local search algorithm is proposed to extract characters that are wrongly identified by the classifiers. An efficient pruning method, which combines component trees and recognition results, is proposed to prune repeating components. A cascaded method combines text line entropy with a Convolutional Neural Network model. It is used to verify text candidates, which reduces the number of non -text regions. The proposed technique is test on three public datasets, i.e. ICDAR2011 dataset, ICDAR2013 dataset and ICDAR2015 dataset. The experimental results show that our approach achieves state-of-the-art performance. (C) 2017 Elsevier B.V. All rights reserved.

 ISSN: 0925-2312

 eISSN: 1872-8286

 IDS Number: EP4TF

 Unique ID: WOS:000397372100029

*Click Here to View Full Record