一种新的结合环状区域划分的特征描述子

doi:10.3969/j.issn.1001-2400.2016.02.012

西安电子科技大学学报 ›› 2016, Vol. 43 ›› Issue (2): 64-69.doi: 10.3969/j.issn.1001-2400.2016.02.012

一种新的结合环状区域划分的特征描述子

黎剑兵1;肖潇2;李小平1;侯晓丽2

(1. 西安电子科技大学空间科学与技术学院，陕西西安 710071;
2. 西安电子科技大学通信工程学院，陕西西安 710071)

收稿日期:2014-12-05 出版日期:2016-04-20 发布日期:2016-05-27
通讯作者: 黎剑兵
作者简介:黎剑兵(1975-)，男，讲师，E-mail: jbli@mail.xidian.edu.cn．
基金资助:
国家自然科学基金资助项目(61403291，61403292)；中央高校基本科研业务费专项资金资助项目(7214390604)

Local coordinate gradient descriptor based on cyclic division

LI Jianbing1;XIAO Xiao2;LI Xiaoping1;HOU Xiaoli2

(1. School of Aerospace Science ＆ Technology, Xidian Univ., Xi'an 710071, China;
2. School of Telecommunication Engineering, Xidian Univ., Xi'an 710071, China)

Received:2014-12-05 Online:2016-04-20 Published:2016-05-27
Contact: LI Jianbing

摘要/Abstract

摘要：

为提高图像特征描述子的仿射不变性及匹配性能，提出了一种特征区域描述方法．首先，该方法用Hessian-affine特征检测子提取特征区域，将其归一化为单位圆特征区域以满足仿射不变性；然后，采用环形区域划分方法且在图像样本点的局部坐标系上统计梯度方向，这样，不仅满足了旋转不变性，而且避免了直方图统计主方向带来的误差．实验结果表明，新方法不仅具有良好的仿射不变性，而且在匹配性能上明显优于尺度不变特征描述子．

关键词: 计算机视觉, 局部特征描述, 仿射不变性, 局部坐标系

Abstract:

A novel regional image feature description method is proposed to improve the affine invariant and matching performance of image feature descriptors. Firstly, the Hessian-affine detector is adopted to extract the image feature region,which is normalized to the unit circular feature region to meet the affine invariant requirement. Secondly, in order to avoid the error caused by calculating main gradient orientation on the histogram, the annular-based region division is proposed on the local coordinate system of the image sample point to calculate the local gradient orientation. Experimental results demonstrate that the new method not only has an excellent affine invariant,but also is significantly better than the SIFT descriptor in match performance.

Key words: computer vision, local feature, affine invariant, local coordinate

中图分类号:

TP391

黎剑兵;肖潇;李小平;侯晓丽. 一种新的结合环状区域划分的特征描述子[J]. 西安电子科技大学学报, 2016, 43(2): 64-69.

LI Jianbing;XIAO Xiao;LI Xiaoping;HOU Xiaoli. Local coordinate gradient descriptor based on cyclic division[J]. Journal of Xidian University, 2016, 43(2): 64-69.

参考文献

［1］王鹏, 王平, 沈振康, 等. 一种基于SIFT的仿射不变特征提取新方法［J］. 信号处理, 2011, 27(1): 87-93.
WANG Peng, WANG Ping, SHEN Zhenkang, et al. A Novel Algorithm for Affine Invariant Feature Extraction Based on SIFT［J］. Signal Processing, 2011, 27(1): 87-93.
［2］颜雪军, 赵春霞, 袁夏, 等. 2DPCA-SIFT: 一种有效的局部特征描述方法［J］.自动化学报, 2014, 40(4): 675-682.
YAN Xuejun, ZHAO Chunxia, YUAN Xia, et al. 2DPCA-SIFT: an Efficient Local Feature Descriptor［J］. Acta Automatica Sinica, 2014, 40(4): 675-682.
［3］ HUANG Z Y, KANG W X, WU Q X, et al. A New Descriptor Resistant to Affine Transformation and Monotonic Intensity Change［J］. Computer Vision and Image Understanding, 2014, 120(2): 117-125.
［4］ FAN B, WU F C, HU Z Y. Aggregating Gradient Distributions into Intensity Orders: a Novel Local Image Descriptor［C］//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition: 3. Piscataway: IEEE, 2011: 2377-2384.
［5］ XU X W, TIAN L, FENG J J, et al. OSRI: a Rotationally Invariant Binary Descriptor［J］. IEEE Transactions on Image Processing, 2014, 7(23): 2983-2995.
［6］ FAN B, WU F, HU Z. Rotationally Invariant Descriptors Using Intensity Order Pooling［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 10(34): 2031-2045.
［7］万国挺, 王俊平, 曹洪花, 等. 一种区间限定预检测的误配点剔除算法［J］. 西安电子科技大学学报, 2013, 40(5): 107-112.
WAN Guoting, WANG Junping, CAO Honghua, et al. Efficient Algorithm for Mismatching Point Elimination with Interzone Limited Pre-testing［J］. Journal of Xidian University, 2013, 40(5): 107-112.
［8］ BROWN M, HUA G, WINDER S. Discriminative Learning of Local Image Descriptors［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(1): 43-57.
［9］ MIKOLAJCZYK K, SCHMID C. Scale ＆ Affine Invariant Interest Point Detectors［J］. International Journal of Computer Vision, 2004, 60(1): 63-86.
［10］颜雪军, 赵春霞, 袁夏, 等. 一种鲁棒的基于图像对比度的局部特征描述方法［J］. 电子与信息学报, 2014, 36(4): 882-887.
YAN Xuejun, ZHAO Chunxia, YUAN Xia, et al. A Robust Local Feature Descriptor Based on Image Contrast［J］. Journal of Electronics ＆ Information Technology, 2014, 36(4): 882-887.
［11］ MIKOLAJCZYK K, TUYTELAARS T, SCHMID C, et al. A Comparison of Affine Region Detectors［J］. International Journal of Computer Vision, 2005, 65(1): 43-72.
［12］ FAN B, KONG Q Q, TRZCINSKI T, et al. Receptive Fields Selection for Binary Feature Description［J］. IEEE Transactions on Image Processing, 2014, 23(6): 2583-2595.
［13］ WANG Z H, FAN B, WU F C. Local Intensity Order Pattern for Feature Description［C］//Proceedings of 2011 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2011: 603-610.
［14］ MIKOLAJCZYK K, SCHMID C. A Performance Evaluation of Local Descriptors［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
［15］ SIMONYAN K, VEDALDI A, ZISSERMAN A. Learning Local Feature Descriptors Using Convex Optimisation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(8): 1573-1585.

一种新的结合环状区域划分的特征描述子

Local coordinate gradient descriptor based on cyclic division

PDF (PC)

赞

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 1

Metrics

本文评价

推荐阅读 10