Table of Content

Open Access

ARTICLE

A Method of Text Extremum Region Extraction Based on JointChannels

Xueming Qiao1, Yingxue Xia1, Weiyi Zhu2, Dongjie Zhu3, *, Liang Kong1, Chunxu Lin3, Zhenhao Guo3, Yiheng Sun3
1 State Grid Weihai Power Supply Company, Weihai, China.
2 State Grid Shandong Electric Power Company, Jinan, China.
3 School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China.
* Corresponding Author: Dongjie Zhu. Email: .

Journal on Artificial Intelligence 2020, 2(1), 29-37. https://doi.org/10.32604/jai.2020.09955

Received 03 February 2020; Accepted 05 March 2020; Issue published 15 July 2020

Abstract

Natural scene recognition has important significance and value in the fields of image retrieval, autonomous navigation, human-computer interaction and industrial automation. Firstly, the natural scene image non-text content takes up relatively high proportion; secondly, the natural scene images have a cluttered background and complex lighting conditions, angle, font and color. Therefore, how to extract text extreme regions efficiently from complex and varied natural scene images plays an important role in natural scene image text recognition. In this paper, a Text extremum region Extraction algorithm based on Joint-Channels (TEJC) is proposed. On the one hand, it can solve the problem that the maximum stable extremum region (MSER) algorithm is only suitable for gray images and difficult to process color images. On the other hand, it solves the problem that the MSER algorithm has high complexity and low accuracy when extracting the most stable extreme region. In this paper, the proposed algorithm is tested and evaluated on the ICDAR data set. The experimental results show that the method has superiority.

Keywords

Feature extraction, scene text detection, scene text feature extraction, extreme region.

Cite This Article

X. Qiao, Y. Xia, W. Zhu, D. Zhu, L. Kong et al., "A method of text extremum region extraction based on jointchannels," Journal on Artificial Intelligence, vol. 2, no.1, pp. 29–37, 2020.



This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1331

    View

  • 1136

    Download

  • 0

    Like

Related articles

Share Link

WeChat scan