您的位置:首页  > 论文页面

自然场景下的任意方向文本检测算法研究

发表时间:2022-06-27  浏览量:249  下载量:18
全部作者: 杨雪莹,刘勇
作者单位: 北京邮电大学信息与通信工程学院
摘 要: 针对自然场景中的文本检测任务目前存在的几个难点展开重点研究,在已有文本检测算法的基础上,提出了一种基于锚的任意方向文本检测方法,对传统的区域建议网络(region proposal network,RPN)进行改进,使之可以生成含有方向角度信息的锚框。方法还利用仿射变换将RPN生成的带有旋转角度的候选区域映射到特征图上,并使用双线性插值来消除量化带来的误差。该方法多用于检测自然场景中带有一定倾斜角度的文本。实验结果表明,在ICDAR2015数据集上,本文提出的基于锚的任意方向文本检测方法的精确率为0.88,召回率为0.77,F-measure为0.82,优于大部分现有的基于锚的文本检测方法,并且该方法对小尺寸文本的检测效果极佳。
关 键 词: 人工智能;文本检测;深度学习;仿射变换;计算机视觉
Title: Arbitrary direction text detection algorithm in natural scene
Author: YANG Xueying, LIU Yong
Organization: (School of Information and Communication Engineering, Beijing University of Posts and Telecommunications
Abstract: This paper focuses on several difficulties existing in natural scene text detection. Based on the existing text detection algorithms, an anchor-based arbitrary direction text detection method is proposed. The traditional region proposal network (RPN) is improved to generate anchor box with direction and angle information. In addition, the text proposals with rotation angles generated by RPN are projected to feature map using affine transformation, and the errors caused by quantization are eliminated using bilinear interpolation. The method proposed in this paper is mostly applied to detect texts with an oblique angle in natural scenes. The experimental results, on the ICDAR2015 dataset, show that the accuracy of the anchor-based arbitrary direction text detection method proposed in this paper is 0.88, the recall is 0.77, and the F-measure is 0.82, which is better than most existing anchor-based text detection methods, and this method has excellent effect on small-scale text detection.
Key words: artificial intelligence; text detection; deep learning; affine transformation; computer vision
发表期数: 2022年6月第2期
引用格式: 杨雪莹,刘勇. 自然场景下的任意方向文本检测算法研究[J]. 中国科技论文在线精品论文,2022,15(2):241-250.
 
1 评论数 0
暂无评论
友情链接