基于局部边缘二值模式的图像检索  

Image retrieval based on local edge binary pattern

作　　者：毋小省[1] 孙君顶[1,2] 

机构地区：[1]河南理工大学计算机科学与技术学院,河南焦作454000 [2]江苏省图像处理与图像通信重点实验室,江苏南京210003

出　　处：《光电子．激光》2013年第1期184-189,共6页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金(61005033);教育部科学技术研究重点计划(210128);河南省骨干教师资助计划(2010GGJS-059);江苏省重点实验室基金(LBEK2011002)资助项目

摘　　要：在定义局部边缘的基础上提出了局部边缘二值模式(LEBP),并结合Gabor滤波器将其扩展到多分辨率LEBP(MLEBP)。对传统的中心对称局部二值模式(CS-LBP)和方向局部二值模式(D-LBP)进行了改进,新描述符在不增加计算复杂度和提高特征维数的基础上,进一步融入了局部边缘信息。为验证新描述符的性能,采用3个通用的纹理图像库进行图像检索实验。结果表明,结合本文方法,明显提高了传统描述符的分辨能力。In order to describe the image texture feature efficiently, a new extension of local binary pattern （LBP） is proposed for texture image retrieval in this paper. Firstly,a new definition of image local edge is introduced according to the gray-level variation between the central pixel and its neighbors in an image neighborhood. Then, the new method, called local edge binary pattern （LEBP） ,is presented, which fuses the advantages of LBP and local edge information. After that, the two region operators, center-symmetric local binary pattern （CS-LBP） and direction local binary pattern （DLBP） ,are improved to center-symmetric local edge binary pattern （CS-LEBP） and direction local edge binary pattern （DLEBP） respec tively without increasing the computational complexity or feature dimension. Finally, LEBP is further ex tened by combining with Gabor filter. In order to prove the performance of the descriptors mentioned in the paper, three widely used texture databases are chosen for test. The experimental results prove that CS-LBP and D-LBP can be greatly improved if they combine with the proposed LEBP. Furthermore, the multiresolution operators can get better performance than the traditional LBP with less feature dimension.

关 键 词：图像检索 局部二值模式(LBP) 局部边缘二值模式(LEBP) GABOR滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]