文章基本信息

标题：Local Tri-directional Weber Rhombus Co-occurrence Pattern: A New Texture Descriptor for Brodatz Texture Image Retrieval
本地全文：下载
作者：Venkata Satya Kumar Gangavarapu ; Gopala Krishna Mohan Pillutla
期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2016
卷号：5
期号：6
页码：1751-1755
出版社：Shri Pannalal Research Institute of Technolgy
摘要：A new feature extraction method called Local Tri-directional Weber Rhombus Co-occurrence Pattern (LTriWRCoP) for texture image retrieval is presented in the paper. Most of the local binary pattern (LBP) variants extract the local information based on difference of current pixel with its neighborhood pixels but they ignore the original intensity of the stimulus. The proposed LTriWRCoP not only explores the inter relationship among the neighborhood pixels but also considers the original intensity of stimulus for extracting the local information structure. Further, gray level co occurrence matrix (GLCM) is used to get the co occurrences of pixel pairs in local pattern map as it is more robust than the frequency of patterns obtained using histogram. The proposed method also examine the co-occurrence of pixel pairs in various directions and distances. The experimental results on the Brodatz texture database reveals the superiority of the proposed method to the other methods in terms of average precision and recall rates
关键词：GLCM; Im age retrieval; Local binary pattern ; ; Pattern recognition ;Texture