Region Growth Segmentation Based on Dual-cores

摘要：

In Image segmentation, the boundary of threshold segmentation would be deviated from the true edge points with regional growth segmentation, which based on dual cores is proposed employing local contrast information. By analyzing the threshold segmentation and edge detection segmentation, the fused segmentation algorithm is proposed integrating of them. Region growing segmentation based on dual-core is researched, the Gaussian noise effect on the segmentation is analyzed, and contrast with Otsu segmentation or Sobel operator segmentation; the dual-core segmentation principle is analyzed, high and low threshold segmentation method is designed. The characteristics of the transition region are studied; and whose pixels assigned algorithm is designed based on the local contrast. Experimental results show that the algorithm not only considers the adjacent uniformity of image information, but also takes into account the local contrast, which improves the effect of a simple threshold; it is an effective and practical image segmentation algorithm.

关键词： image segmentation Otsu method threshold value gradient dual cores

作者: Junchai Gao Zhiyong Lei Zemin Wang Keding Yan

作者单位: School of Electronic Information Engineering Xian Technological University Xi an, Shaanxi, 710032, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information and Industrial Electronics(2011年信息与工业电子国际会议 ICIIE 2011)

会议地点: 成都

会议语种:英文

页码: 219-223

在线出版日期: 2011-01-14（万方平台首次上网日期，不代表论文的发表时间）