基于等距环局部二值模式的特征描述子

doi:10.3969/j.issn.1000-3428.2017.01.047

计算机工程

基于等距环局部二值模式的特征描述子

喻强,聂洪玉,张晶晶

(西南交通大学信息科学与技术学院,成都 611756)

收稿日期:2015-11-18 出版日期:2017-01-15 发布日期:2017-01-13
作者简介:喻强(1991—),男,硕士研究生,主研方向为数字图像处理;聂洪玉、张晶晶,硕士研究生。
基金资助:
国家自然科学基金(61461048);国家社会科学基金(12EF119);西藏自治区科技厅科技计划重点项目(Z2013B28G28/02)。

Feature Descriptor Based on Local Binary Pattern with Equidistant Ring

YU Qiang,NIE Hongyu,ZHANG Jingjing

(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China)

Received:2015-11-18 Online:2017-01-15 Published:2017-01-13

摘要/Abstract

摘要： 现有的描述子一般与主方向相关,当图像经过变换时,得到的描述子主方向会有误差,从而导致图像匹配效果不理想。针对上述问题,基于等距环局部二值模式,提出一种二进制描述子构造方法。在构造描述子与描述子匹配过程中分别使用了等距环局部二值采样模式与分组匹配策略,使得构造的描述子具有旋转不变性,解决主方向问题和加速匹配过程。实验结果表明,与BRIEF,BRISK等二进制描述子相比,该方法具有更快的速度及更高的准确率。

关键词: 图像变换, 局部二值模式, 二进制描述子, 采样模式, 分组匹配, 旋转不变性

Abstract: Existing descriptors are generally associated with principal direction.When the images are transformed,deviation usually occurs in the principal direction of the descriptors,which leads to unsatisfactory image matching results.In order to solve this problem,a binary descriptor construction method based on Local Binary Pattern(LBP) with equidistant rings is proposed.The sampling model of Equidistant Ring Local Binary Pattern(ErLBP) and matching strategy of grouping are introduced into descriptor constructing and matching,so that the descriptor is rotation-invariant.In this way,the principal direction problem is solved and the speed of descriptor matching is improved.Experimental results show that this method is more accurate and speedy compared with other state-of-the-art binary descriptors,such as BRIEF,BRISK.

Key words: image transformation, Local Binary Pattern(LBP), binary descriptor, sampling mode, grouping matching, rotation invariance

中图分类号:

TP391

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, doi: 10.3969/j.issn.1000-3428.2017.01.047.

YU Qiang,NIE Hongyu,ZHANG Jingjing. Feature Descriptor Based on Local Binary Pattern with Equidistant Ring[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.01.047.

https://www.ecice06.com/CN/Y2017/V43/I1/274

参考文献

参考文献［1］Lowe D G.Distinctive Image Features from Scale-invariant Keypoints［J］.International Journal of Computer Vision,2004,60(2):91-110. ［2］Bay H,Tuytelaars T,Cool L V.SURF:Speeded Up Robust Features［C］//Proceedings of the 9th European Conference on Computer Vision.Berlin,Germany:Springer-Verlag,2006:404-417. ［3］Torralba A,Fergus R,Weiss Y.Small Codes and Large Image Databases for Recognition［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8. ［4］Jegou H,Douze M,Schmid C.Improving Bag-of-features for Large Scale Image Search［J］.International Journal of Computer Vision,2010,87(3):316-336. ［5］Trzcinski T,Lepetit V.Efficient Discriminative Pro-jections for Compact Binary Descriptors［C］//Pro-ceedings of the 12th European Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2012:228-242. (下转第286页) (上接第279页) ［6］Strecha C,Bronstein A,Bronstein M,et a1.LDAHash:Improved Matching with Smaller Descriptors［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):66-78. ［7］Trzcinski T,Christoudias M,Fua P,et a1.Boosting Binary Keypoint Descriptors［C］//Proceedings of IEEE Con-ference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2874-288. ［8］Calonder M,Lepetit V,Strecha C,et a1.BRIEF:Binary Robust Independent Elementary Features［C］//Pro-ceedings of the 1lth European Conference on Computer Vision.Berlin,Germany:Springer-Verlag,2010:778-792. ［9］Rublee E,Rabaud V,Kanolige K,et al.ORB:An Efficient Alternative to SIFT or SURF［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:2564-2571. ［10］Leutenegger S,Chli M,Siegwart R Y.BRISK:Binary Robust Invariant Scalable Keypoints［C］//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:2548-2555. ［11］Alahi A,Ortiz R,Vandergheynst P.FREAK:Fast Retina Keypoint［C］//Proceedings of IEEE Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:510-517. ［12］卢鸿波,孙愿,张志敏．采用旋转匹配的二进制局部描述子［J］.中国图象图形学报,2013,18(10):1315-1321. ［13］Oja1a T,Pietikainen M,Maenpaa 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. ［14］Heikkila M,Pietikainen M,Schmid C.Description of Interest Regions with Local Binary Patterns［J］.Pattern Recognition,2009,42(3):425-436. ［15］Rosten E,Drummond T.Machine Learning for High-speed Corner Detection［C］//Proceedings of the 9th European Conference on Computer Vision.Berlin,Germany:Springer-Verlag,2006:430-443. ［16］Mikolajczyk K,Schmid C.A Performance Evaluation of Local Descriptors［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630. 编辑刘冰

[1]	张玉婷, 向海昀, 李倩, 廖浩德. 基于稳定Adam和空间域变换的对抗样本生成算法[J]. 计算机工程, 2024, 50(1): 251-258.
[2]	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.
[3]	许嘉麟, 姚双, 张蕊华, 许浩, 沈洋. 基于亲疏度矩阵的点云置换不变特征提取方法[J]. 计算机工程, 2022, 48(6): 243-250.
[4]	蔡李美, 李新福, 田学东. 基于分层图像融合的虚拟视点绘制算法[J]. 计算机工程, 2021, 47(4): 204-210.
[5]	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.
[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]	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.
[8]	严宇,宋威,朱华东. 基于颜色基元共生矩阵的旋转图像检索[J]. 计算机工程, 2017, 43(5): 217-223.
[9]	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.
[10]	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.
[11]	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.
[12]	娄达平,王晓东,富显祖,章联军. 基于深度图像分割的虚拟视点绘制[J]. 计算机工程, 2016, 42(10): 12-19.
[13]	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.
[14]	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, 2015, 41(4): 210-216.
[15]	袁紫华,李峰,周书仁. 基于Haar 型LBP 纹理特征的人体姿态估计[J]. 计算机工程, 2015, 41(4): 199-204.

选择文件类型/文献管理软件名称

选择包含的内容

基于等距环局部二值模式的特征描述子

Feature Descriptor Based on Local Binary Pattern with Equidistant Ring

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于等距环局部二值模式的特征描述子

Feature Descriptor Based on Local Binary Pattern with Equidistant Ring

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价