Please wait a minute...
浙江大学学报(工学版)
J4  2011, Vol. 45 Issue (4): 596-601    DOI: 10.3785/j.issn.1008-973X.2011.04.002
    
Image retrieval and recognition based on generalized
local distance functions
GU Hong, ZHAO Guang-zhou
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

A metric distance of images called generalized local distance function was proposed for the image distances computation aiming at the most commonly local feature descriptors. The distance had two parts, the feature-to-image distance and the image-to-image distance. The image-to-image distance was defined as a combination of feature-to-image distances, where the feature-to-image distance was computed according to the knearest neighbor distances of that feature. The feature-to-image distance was represented in several ways with different constraint assumptions. The distance function can be learned by a quadratic optimization problem based on relative comparisons. Then Adaboost was used to ensemble the learned distance functions to obtain a final image classifier. The generalized local distance overcomes the shortcoming of original linear local distance function, for which most of the statistical information is lost. Experimental results show that the method significantly improves the image categorization performance.

Published: 05 May 2011
CLC:  TP 181  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

GU Hong, ZHAO Guang-zhou. Image retrieval and recognition based on generalized
local distance functions. J4, 2011, 45(4): 596-601.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.04.002     OR     https://www.zjujournals.com/eng/Y2011/V45/I4/596


广义局部图像距离函数下的图像分类与识别

针对当前常用的局部特征算子,提出广义的局部图像距离函数用于计算图像间的距离.广义局部图像距离函数主要由2部分组成：特征到图像的距离以及图像到图像的距离.其中图像到图像的距离定义为特征到图像距离的线性组合.特征到图像的距离与该特征在图像中的k个最邻近特征距离相关,在不同的约束假设下具有不同的表达形式.该距离函数可以通过求解基于相对约束的二次优化问题进行学习.学习后的距离函数通过Adaboost方法集成为强分类器用于图像分类.广义局部图像距离函数克服了简单线性距离函数下特征统计信息丢失的问题,实验数据证明,该方法有效提高了图像分类的性能.

［1］ DATTA R, JOSHI D, LI J, et al. Image retrieval: ideas, influences, and trends of the new age ［J］. ACM Computing Surveys, 2008, 40(2): 1-60.
［2］ LOWE D G. Distinctive image features from scaleinvariant keypoints ［J］. International Journal of Computer Vision, 2004, 60(2): 91-110.
［3］ DALAI N, TRIGGS B, RHONEALPS I, et al. Histograms of oriented gradients for human detection ［C］∥ Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 1063-6919.
［4］ BERG A C, BERG T L, MALIK J. Shape matching and object recognition using low distortion correspondences ［C］∥ Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 26-33.
［5］ SIVIC J, ZISSERMAN A. Video google: a text retrieval approach to object matching in videos ［C］∥ Proceedings of the 9th IEEE International Conference on Computer Vision. Madison, Wisconsin: IEEE, 2003: 1470-1477.
［6］ GRAUMAN K, DARRELL T. The pyramid match kernel: discriminative classification with sets of image features ［C］∥ Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing: IEEE, 2005: 1288-1296.
［7］ 徐磊,赵光宙,顾弘.基于支持向量机和多球体的一对多分类器［J］.浙江大学学报：工学版,2009,43(2): 303-308.
XU Lei, ZHAO Guangzhou, GU Hong. Novel onevsrest classifier based on SVM and multispheres \
[J\]. Journal of Zhejiang University: Engineering Science, 2009, 43(2): 303-308.
［8］ 徐磊,赵光宙,顾弘.基于作用集的一类支持向量机递推式训练算法［J］.浙江大学学报：工学版,2009,43(1): 42-46.
XU Lei, ZHOAO Guangzhou, GU Hong. Recurive training algorithm for oneclass support vector machine based on active set method \
[J\]. Journal of Zhejiang University: Engineering Science, 2009, 43(1): 42-46.
［9］ FEIFEI L, FERGUS R, PERONA P. Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories ［J］. Computer Vision and Image Understanding, 2007, 106(1): 59-70.
［10］ FROME A, SINGER Y, SHA F, et al. Learning globallyconsistent local distance functions for shapebased image retrieval and classification ［C］∥ Proceedings of the 11th IEEE International Conference on Computer Vision. Rio de Janeiro, Brazil: IEEE, 2007: 1255-1263.
［11］ BOIMAN O, SHECHTMAN E, IRANI M. In defense of nearestneighbor based image classification ［C］∥ Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, Alaska: IEEE, 2008: 1-8.
［12］ VARMA M, RAY D. Learning the discriminative powerinvariance tradeoff ［C］∥ Proceedings of the IEEE International Conference on Computer Vision. Minneapolis, USA: IEEE， 2007: 1-8.
［13］ FROME A, SINGER Y, MALIK J. Image retrieval and classification using local distance functions ［C］∥ Proceedings of the 20th Annual Conference on Neural Information Processing Systems. Vancouver, Canada: MIT, 2006: 417-425.
［14］ GRAUMAN K, DARRELL T. The pyramid match kernel: efficient learning with sets of features ［J］. The Journal of Machine Learning Research, 2007, 8(1): 725-760.
［15］ HIFSTER E, LIENHART R, SLANEY M. Image retrieval on largescale image databases ［C］∥ Proceedings of the 6th ACM International Conference on Image and Video Retrieval. Amsterdam, Netherlands: ACM, 2007: 17-24.
［16］ CHEN Y, WANG J Z. Image categorization by learning and reasoning with regions ［J］. The Journal of Machine Learning Research, 2004(5): 913-939.
［17］ VIOLA P, JONES M J. Robust realtime face detection ［J］. International Journal of Computer Vision, 2004, 57(2): 137-154.
［18］ FREUND Y, SCHAPIRE R, ABE N. A short introduction to boosting ［J］. Journal of Japanese Society for Artificial Intelligence, 1999, 14(5): 771-780.
［19］ FEIFEI L, PERONA P. A Bayesian hierarchical model for learning natural scene categories ［C］∥ Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern R
[1] LIN Yi-ning, WEI Wei, DAI Yuan-ming. Semi-supervised Hough Forest tracking method[J]. J4, 2013, 47(6): 977-983.
[2] LI Kan, HUANG Wen-xiong, HUANG Zhong-hua. Multi-sensor detected object classification method based on
support vector machine[J]. J4, 2013, 47(1): 15-22.
[3] WANG Hong-bo, ZHAO Guang-zhou, QI Dong-lian, LU Da. Fast incremental learning method for one-class support vector machine[J]. J4, 2012, 46(7): 1327-1332.
[4] AI Jie-qing, GAO Ji, PENG Yan-bin, ZHENG Zhi-jun. Negotiation decision model based on transductive
support vector machine[J]. J4, 2012, 46(6): 967-973.
[5] PAN Jun, KONG Fan-sheng, WANG Rui-qin. Locality sensitive discriminant transductive learning[J]. J4, 2012, 46(6): 987-994.
[6] JIN Zhuo-jun, QIAN Hui, ZHU Miao-liang. Trajectory evaluation method based on intention analysis[J]. J4, 2011, 45(10): 1732-1737.
[7] LUO Jian-hong, CHEN De-zhao. Application of adaptive ensemble algorithm based on
correctness and diversity[J]. J4, 2011, 45(3): 557-562.
[8] SHANG Xiu-Qin, LEI Jian-Gang, SUN You-Xian. Genetic programming based twoterm prediction model of iron ore burning through point[J]. J4, 2010, 44(7): 1266-1269.
[9] XU Lei, DIAO Guang-Zhou, GU Hong. Preprocess method of pairwise coupling based on multi-spheres[J]. J4, 2010, 44(2): 237-242.