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
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.