基于改进WLD 的纹理特征提取方法

doi:10.3969/j.issn.1000-3428.2015.04.040

摘要/Abstract

摘要： 在纹理分类应用背景下,原始韦伯局部描述符(WLD)对纹理模式区分能力有限。针对该问题,提出一种基于正负梯度改进的WLD(WLD-PNG)。利用局部窗内像素点间灰度变化的正负梯度构建纹理特征描述符,通过分离计算正负梯度的差分激励算子,保留灰度等级变化的正负性信息,以增强纹理模式的可区分性,运用均匀局部二值模式(uLBP)提取灰度等级变化的空间分布结构信息,并提高纹理模式的识别能力,使用均匀量化和编码技术将差分激励算子与uLBP 结合,从而描述图像的纹理特征。在Brodatz 和KTH-TIPS2-a 纹理库上进行对比实验,结果表明,与原WLD,uLBP,WLD + uLBP 及已有改进的WLD 等方法相比,WLD-PNG 在提高纹理分类性能的同时,具有较好的稳健性和较低的计算复杂度。

关键词: 纹理分类, 纹理特征, 韦伯局部描述符, 差分激励, 正负梯度, 局部二值模式

Abstract: Aiming at the shortage of the discriminative ability to texture patterns for image texture classification using Weber Local Descriptor(WLD),an improved WLD based on Positive and Negative Gradient Features(WLD-PNG) is proposed. Positive and negative gradients are characterized by computing positive and negative differential excitations for preserving signed grayscale change information,and local texture structure information is represented by uniform Local Binary Patterns(uLBP). Combine both of them to build the image texture feature. The comparing experiments on the Brodatz and KTH-TIPS2-a texture databases demonstrate that WLD-PNG improves the distinctiveness of texture patterns, and has better robustness and lower computational complexity compared with original WLD,uLBP,WLD + uLBP and other improved WLD methods,etc.

Key words: texture classification, texture feature, Weber Local Descriptor(WLD), differential excitation, positive and negative gradient, Local Binary Pattern(LBP)

中图分类号:

TP391. 4

郭仙草,石美红,李青. 基于改进WLD 的纹理特征提取方法[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2015.04.040.

GUO Xiancao,SHI Meihong,LI Qing. Texture Feature Extraction Method Based on Improved WLD[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2015.04.040.

http://www.ecice06.com/CN/Y2015/V41/I4/210

参考文献

参考文献 [ 1 ]　刘　丽,匡纲要. 图像纹理特征提取方法综述[J]. 中国图象图形学报,2009,14(4):622-635. [ 2 ]　Haralick R M, Shanmugam K, Dinstein I. Textural Features for Image Classification[J]. IEEE Transactions on Systems,Man and Cybernetics,1973,3(6):610-621. [ 3 ]　王国德,张培林,任国全,等. 融合LBP 和GLCM 的纹理特征提取方法[J]. 计算机工程,2012,38 (11): 199-201. [ 4 ]　Mallat S G. A Theory for Multiresolution Signal Decomposition:The Wavelet Representation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693. [ 5 ]　Unser M. Texture Classification and Segmentation Using Wavelet Frames [ J ]. IEEE Transactions on Image Processing,1995,4(11):1549-1560. [ 6 ]　He Dongchen, Wang Li. Texture Unit, Texture Spectrum,and Texture Analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28 ( 4 ): 509-512. [ 7 ]　He Dongchen,Wang Li. Simplified Texture Spectrum for Texture Analysis [ J ]. Journal of Communication and Computer,2010,7(8):44-53. [ 8 ]　Varma M, Zisserman A. A Statistical Approach to Material Classification Using Image Patch Exemplars[ J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(11):2032-2047. [ 9 ]　Liu Li, Fieguth P W. Texture Classification from Random Features [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34 ( 3 ): 574-586. [10]　Ojala T,Pietik I M,Harwood D. A Comparative Study of Texture Measures with Classification Based on Feature Distributions [ J ]. Pattern Recognition, 1996, 29(1):51-59. [11]　Chen Jie,Shan Shiguang,He Chu,et al. WLD:A Robust Local Image Descriptor [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9): 1705-1720. [12]　Liu Fan, Tang Zhenmin, Tang Jinhui. WLBP: Weber Local Binary Pattern for Local Image Description [J]. Neurocomputing,2013,120:325-335. [13]　Dawood H, Dawood H, Guo Ping. Combining the Contrast Information with WLD for Texture Classification [ C ] / / Proceedings of IEEE International Conference on Computer Science and Automation Engineering. Washington D. C. , USA: IEEE Press,2012:203- 207. [14]　付　蓉,石美红,徐步高. 基于窗阈值局部二值模式的织物疵点检测算法[J]. 计算机集成制造系统,2010, 16(9):2009-2015. [15]　Huang Di, Shan Caifeng, Ardabilian M, et al. Local Binary Patterns and Its Application to Facial Image Analysis:A Survey[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,2011,41(6):765-781. [16]　Li Shutao, Gong Dayi, Yuan Yuan. Face Recognition Using Weber Local Descriptors [ J]. Neurocomputing, 2013,122:272-283. [17]　Cui Shiyong, Dumitru C O, Datcu M. Ratio-detectorbased Feature Extraction for Very High Resolution SAR Image Patch Indexing[J]. IEEE Geoscience and Remote Sensing Letters,2013,10(5):1175-1179. [18]　Gragnaniello D,Poggi G,Sansone C,et al. Fingerprint Liveness Detection Based on Weber Local Image Descriptor [ C ] / / Proceedings of IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications. Napoli,Italy:IEEE Press,2013: 46-50. [19]　Hussain M, Muhammad G, Saleh S Q, et al. Image Forgery Detection Using Multi-resolution Weber Local Descriptors [ C ] / / Proceedings of EUROCON ’ 13. Zagreb,Yugoslavia:IEEE Press,2013:1570-1577. [20]　郭大洲. 基于韦伯局部特征和形状上下文的图像识别与匹配算法[D]. 天津:天津大学,2010. [21]　Ojala T,Pietik I M,Menp T. Multiresolution Gray-scale and Rotation Invariant Texture Classification with Local Binary Patterns [ J ]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24 ( 7 ): 971-987. [22]　Jain A. Fundamentals of Digital Image Processing[M]. [S. l. ]:Wiley-Blackwell,1989. [23]　Ojala T, Valkealahti K, Oja E, et al. Texture Discrimination with Multidimensional Distributions of Signed Gray-level Differences[J]. Pattern Recognition, 2001,34(3):727-739. 编辑　刘　冰

[1]	徐正梅, 刘华明, 毕学慧, 王亚. 基于特征优化的无参考光场图像质量评价[J]. 计算机工程, 2023, 49(7): 242-250.
[2]	陈苏阳, 宋晓宁. 融合多尺度特征的多监督人脸活体检测算法[J]. 计算机工程, 2022, 48(12): 79-85,94.
[3]	黄坤, 钱军浩, 王江文. 基于改进FREAK的图像匹配算法[J]. 计算机工程, 2020, 46(8): 250-257.
[4]	曾娅琴, 张琳琳, 张若楠, 杨波. 基于MobileNet的恶意软件家族分类模型[J]. 计算机工程, 2020, 46(4): 162-168.
[5]	李鹏, 陈嘉琦, 马味敏, 叶方跃. Contourlet域下基于多尺度特征的声呐图像分割[J]. 计算机工程, 2019, 45(9): 253-259.
[6]	陈文兵,毛军杰,陈允杰,周林义. ILBP算子在浓雾天气形势图识别中的应用[J]. 计算机工程, 2019, 45(5): 199-204,209.
[7]	王飘,耿国华,杨稳,任健. 结合表面纹理与断裂轮廓的碎片拼接方法[J]. 计算机工程, 2019, 45(2): 315-320.
[8]	谢行雨,王玲. 基于纹理相似栈的超声图像分割方法[J]. 计算机工程, 2019, 45(2): 240-244.
[9]	龚红, 杨发顺, 王代强, 丁召. 一种基于背景加权的多特征融合目标跟踪算法[J]. 计算机工程, 2019, 45(12): 249-256,262.
[10]	杨兴宇,阮怀林. 基于局部二值模式特征的新型干扰识别算法[J]. 计算机工程, 2018, 44(7): 285-290,296.
[11]	喻强,聂洪玉,张晶晶. 基于等距环局部二值模式的特征描述子[J]. 计算机工程, 2017, 43(1): 274-279,286.
[12]	胡丹,周兴社,许婉君,侯志强. 基于深度特征与LBP纹理融合的视觉跟踪[J]. 计算机工程, 2016, 42(9): 220-225.
[13]	唐晓晴,刘亚洲,陈骏龙. 基于稀疏表示的遥感图像分类方法改进[J]. 计算机工程, 2016, 42(3): 254-258,265.
[14]	王铁君,王维兰. 基于多特征融合的唐卡图像法器识别方法[J]. 计算机工程, 2016, 42(3): 198-203,207.
[15]	孙玉,刘贵全. 基于HOG与LBP特征的人脸识别方法[J]. 计算机工程, 2015, 41(9): 205-208,214.

选择文件类型/文献管理软件名称

选择包含的内容