基于色彩聚类的自然场景文本检测
Text detection from natural scene images based on color clustering
摘要
Abstract
Considering that the natural scene images have complex background and the text in them is usually various, a text detection method based on color clustering was proposed. The procedures are as follows. Firstly,K-means was utilized to group pixels in color images into five different color layers and the bounding-boxes of connected-components in every color layer were obtained. Some non-text components were removed by analyzing geometrical properties of the bounding-boxes. Subsequently, the scattered components were connected to form candidate text blocks according to their bounding-boxes’ geometrical properties and locations. Finally, text verification was performed by geometrical and edge density identifications. The experimental results show that the proposed method is feasible and effective.关键词
场景文本检测/色彩聚类/文本验证Key words
scene text detection/color clustering/text verification分类
信息技术与安全科学引用本文复制引用
吴慧,赵于前,李香花,邹北骥,邹润民..基于色彩聚类的自然场景文本检测[J].中南大学学报（自然科学版）,2015,(6):2098-2103,6.基金项目
国家自然科学基金资助项目(61172184,61174210,61379107,61402539)；新世纪优秀人才支持计划项目(NCET130603)；高等学校博士学科点专项科研基金资助项目(20130162110016)；湖南省科技基本建设项目(20131199)；中南大学中央高校基本科研业务费专项资金资助项目(2015zzts052)(Projects (61172184,61174210,61379107,61402539) supported by the National Natural Science Foundation of China （61172184,61174210,61379107,61402539）
Project (NCET130603) supported by Program for New Century Excellent Talents in University （NCET130603）
Project (20130162110016) supported by the Specialized Research Fund for the Doctoral Program of Higher Education （20130162110016）
Project (20131199) supported by Science and Technology Basic Construction of Hunan Province （20131199）
Project (2015zzts052) supported by the Fundamental Research Funds for the Central Universities of Central South University) （2015zzts052）
