MSER Fast Skewed Scene-text Location Algorithm

Aiming at the problem that text localization requires a large number of training samples in natural scenes, which leads to low speed of algorithm running and it is difficult to locate skewed text, a fast natural scene skewed text localization algorithm based on maximally stable extremal regions (MSE...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHANG Kai-yu, SHAO Kang-yi, LU Di
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2019-04-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=1663
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aiming at the problem that text localization requires a large number of training samples in natural scenes, which leads to low speed of algorithm running and it is difficult to locate skewed text, a fast natural scene skewed text localization algorithm based on maximally stable extremal regions (MSER) with hierarchical clustering is proposed . The method of MSER ellipse fitting is used to select the maximally stable extremal regions of the images, and according to the characteristics of the fitting ellipse and its position on the images, the majority of non-text regions are filtered out and the text candidate regions are selected. By using the idea of hierarchical clustering, the text regions can be clustered gradually and merged into text regions rapidly. Finally the individual text regions are merged into word regions, which can achieve efficient localization of skewed scenes. Experimental results show that the speed of this algorithm has improved significantly without loss of locating accuracy compared with traditional positioning algorithms.
ISSN:1007-2683