首页 | 本学科首页   官方微博 | 高级检索  
     

基于LBP-GLCM纹理特征提取的服装图像检索
引用本文:李玥灵,吴国平,耿秀秀,杜晓骏. 基于LBP-GLCM纹理特征提取的服装图像检索[J]. 电视技术, 2015, 39(12): 99-103
作者姓名:李玥灵  吴国平  耿秀秀  杜晓骏
作者单位:中国地质大学(武汉)机电学院,湖北武汉,430074
基金项目:基于流行学习进行图结构设计的高光谱图像分类技术研究
摘    要:提出了一种针对服装图像检索的LBP-GLCM纹理特征提取方法,首先利用Uniform-旋转不变局部二值模式算法处理服装图像,得到不会因为旋转而改变的编码图像,然后获取此图像的灰度共生矩阵,采用能量、对比度、相关性和均匀性描述图像的纹理特征.实验数据表明,LBP-GLCM纹理特征提取方法具有良好的抗旋转性,且在采用欧氏距离作为相似性度量时,LBP-GLCM相较于GLCM纹理特征提取方法可以获得更高的检索效率和准确率.

关 键 词:局部二值模式  灰度共生矩阵  LBP-GLCM  纹理特征提取  服装图像检索
收稿时间:2014-10-08
修稿时间:2014-11-14

Clothing Image Retrieval Based on LBP-GLCM Texture Feature Extraction
liyueling,wuguoping,gengxiuxiu and duxiaojun. Clothing Image Retrieval Based on LBP-GLCM Texture Feature Extraction[J]. Ideo Engineering, 2015, 39(12): 99-103
Authors:liyueling  wuguoping  gengxiuxiu  duxiaojun
Affiliation:Faculty of Mechanical and Electronic Information, China University of Geosciences (Wuhan),Faculty of Mechanical and Electronic Information, China University of Geosciences (Wuhan),Faculty of Mechanical and Electronic Information, China University of Geosciences (Wuhan),Faculty of Mechanical and Electronic Information, China University of Geosciences (Wuhan)
Abstract:A LBP-GLCM texture feature extraction method for clothing image retrieval is presented. First, the clothing image is processed by uniform invariant LBP to obtain the encoded image that does not change its features with the rotation. Then we calculate the statistics GLCM for this image and describe the image texture features with energy, contrast, correlation, and homogeneity. Experimental result indicates this LBP-GLCM texture feature extraction method possesses good anti-rotation ability. Moreover, LBP-GLCM texture feature extraction method retrieves clothing images more efficient and accurate than GLCM method when using Euclidean distance as the similarity measurement.
Keywords:LBP   GLCM   LBP-GLCM   Texture feature extraction   Clothing image retrieval
本文献已被 万方数据 等数据库收录!
点击此处可从《电视技术》浏览原始摘要信息
点击此处可从《电视技术》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号