Vickers Hardness Image Segmentation Based on Wavelet and Laws Texture Measurement

摘要：

Traditional analysis processing on Vickers hardness image is that the picture edge is mainly fitted to a straight line then analyzed and measured. But hardness picture edge is possible to be curving, which brings a very big fitting error. So this paper proposes a method based on image texture feature to do Vickers hardness image segmentation. We adopt Redundant Wavelet Transform and laws texture measurement algorithm to describe the texture characteristics of the indentation image, forming a n-dimensional feature vector, introducing texture features smoothing algorithm based on quadrant to smooth the features. Finally we combine with the improved k-means clustering algorithm to get texture segmentation result, which avoids the uncertainty introduced by line fitting error and the measurement error of the arithmetic mean of the two impress diagonal length d: and d2.

关键词： RWT laws texture measurement improved k-means clustering algorithm Texture segmentation

作者: Guitang Wang Wenjuan Liu Ruihuang Wang Feng Wang

作者单位: School of Information Engineering, Guangdong University of Technology Guangzhou, P. R. China School of Information Engineering,Guangdong University of Technology Guangzhou, P. R. China

会议类型: 国际会议

会议名称: 2010 Second Asia-Pacific Conference on Information Processing(2010年第二届亚太地区信息处理国际会议 APCIP 2010)

会议地点: 南昌

会议语种:英文

页码: 331-333

在线出版日期: 2010-09-17（万方平台首次上网日期，不代表论文的发表时间）