GPU in texture image processing

摘要：

A GPU based approach has been developped to efficiently calculate texture features based on cooccurrence probabilities. The commomly used matrix based approach(the grey level cooccurrence matrix or GLCM) requires an unreasonable amount of computation, especially for image segmentation purposes. The GPU based approach calculates exactly the same results while significantly decreasing the time to calculate the texture features. This paper describes the implementation of a GPU based algorithm, demonstrates its applicability.

关键词： GPU Computing Co-occurrence Matrix texture

作者: Zhipeng Xu Wenbo Xu

作者单位: School of Physics Science and Information Engineering, Liaocheng University Liaocheng, Shandong, 252 School of Information Technology, Southern Yangtze University Wuxi, Jiangsu, 214122, China

会议类型: 国际会议

会议名称: 2006 International Symposium on Distributed Computing and Applications to Business,Engineering and Science(2006年国际电子、工程及科学领域的分布式计算应用学术研讨会)

会议地点: 杭州

会议语种:英文

页码: 380-383

在线出版日期: 2006-10-12（万方平台首次上网日期，不代表论文的发表时间）