基于颜色信息与区域生长的图像分割新算法  

A Novel Color Image Segmentation Based on Color Information and Region Growing

作　　者：赵钦佩[1] 姚莉秀[1] 程建[1] 何虎翼[1] 杨杰[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200240

出　　处：《上海交通大学学报》2007年第5期802-806,812,共6页Journal of Shanghai Jiaotong University

摘　　要：提出了一种新的结合了颜色特征与区域生长的彩色图像分割算法B-JSEG.该算法是在彩色图像分割的JSEG算法和边缘检测中的方向算子的基础上实现的.根据已有算法的缺陷,利用新的参数描述纹理颜色信息,并通过区域增长和合并来获得最后的分割结果.由于在JSEG算法中加入了方向算子,同时考虑了区域的相似性和边界的非连续性,减少了过分割.大量图像的实验结果表明,所提出的算法具有很好的鲁棒性,比JSEG算法更符合人类的视觉感知.This paper discussed a novel segmentation algorithm B-JSEG for color images based on color information and region growing. This method is proposed on the base of JSEG, a popular method in segmentation of color images, and directional operators for edge detection in images. Compared with other methods existed, new parameters are used to characterize the property of color-texture images in the proposed method. With the aim of alleviating over-segmentation, directional operators are integrated into the JSEG method to take account of both homogeneity and discontinuity in regions. It is shown from the experiments on large amounts of images that the proposed method is robust and able to match better with human＇s perception than JSEG.

关 键 词：彩色图像分割 方向算子 边缘检测 区域生长 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]