[1]SUN Zheng-xing,ZHANG Yao-ye,LI Bin.Applying relevance feedback with a linear programming classifier[J].CAAI Transactions on Intelligent Systems,2007,2(3):34-38.
Copy

Applying relevance feedback with a linear programming classifier

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 2 Number of periods: 2007 3 Page number: 34-38 Column: 学术论文—机器学习 Public date: 2007-06-25
Title:
Applying relevance feedback with a linear programming classifier
Author(s):
SUN Zheng-xing;  ZHANG Yao-ye;  LI Bin 
State Key Lab for Novel Software Technology, Nanjing University, Nanjing 210093 , China
Keywords:
relevance feedback;  feature selection;  linear programming classifier;  sketch retrieval
CLC:
TP391;TP126
DOI:
-
Abstract:
This paper presents a method of applying relevance feedback to an auto mated sketch retrieval system by means of linear programming (LP) classification . A linear programming classifier was designed by combining feature selection wi th classification learning. The proposed classifier not only achieved real-time learning based on small sets of user-annotated samples, but also identified sens itive features from user’s interactive selections according to their contributi on to the classification of candidate sketches, effectively capturing the intent of user feedback with only a small set of training samples giving relevance fee dback. Experiments in sketch retrieval prove that the proposed method is both ef fective and efficient for relevance feedback. 
References:
［1］ ROCCHIO J. Relevance feedback in information retrieval［M］. PrenticeHal l, Inc, 1971.
［2］HUANG T S, ZHOU X S. Image retrieval with relevance feedback: From heuris ti c weight adjustment to optimal learning methods ［A］.International Conference i n Image Processing (ICIP’01)［C］. Thessaloniki, Greece, 2001.
［3］MACARTHUS S D, BRODLEY C E, SHYU C. Relevance feedback decision trees in c on tentbased image retrieval ［A］. Proceedings of IEEE Workshop on ContentBase d Access to Image and Video Libraries［C］.South Carolina, 2000. 
［4］[JP2]COX I J, MILLER M L, MINKA T P,et al. The Bayesian image retrieval sys tem , PicHunter: Theory, implementation and psychophysical experiments ［J］. IEEE Tra nsactions on Image Processing, 2000 , 9(1): 20-37.
［5］HONG P, TIAN Q, HUANG T S. Incorporate support vector machines to content ba sed image retrieval with relevant feedback ［A］. Proceedings of IEEE Internatio nal Conference on Image Processing［C］.Vancouver, Canada, 2000
［6］CHEN Y, ZHOU X S, HUANG T S. Oneclass SVM for learning in image retrieval ［A ］. Proceedings of International Conference on Image Processing［C］. Thessaloni ki, Greece, 2001.
［7］CHU H H, CHI H C, HUANG K Z, et al. Biased support vector machine for rele va nce feedback in image retrieval ［A］. Proceedings of International Joint Confer ence on Neural Networks［C］.Budapest, Hungary, 2004
［8］JAIN A, ZONGKER D. Feature selection: evaluation, application, and small s am ple performance ［J］. IEEE Transactions on Pattern Analysis and Machine Intelli gence, 1997,2(19):153-158.
［9］MANGASARIAN O L. Linear and nonlinear separation of patterns by linear pro gramming ［J］. Operations Research, 1965, 9(5)： 444-452.
［10］BENNETT K P, MANGASARIAN O L. Robust linear programming discrimin ation of t ow linearly inseparable sets ［J］. Optimization Method and Software, 1992, 1(1) : 23-34.
［11］BRADLEY P S, MANGASARIAN O L. Feature selection via concave minimization an d support vector machines ［A］.Proceeding of 5th International Conference on M achine Learning［C］.［s.l.］,1998. 
［12］GUO G, DYER C R. Learning from examples in the small sample case: face ex pression recognition ［J］. IEEE Transactions on Systems Man and Cybernetics, 2 005, 35(3): 477-488.
［13］LIANG S, SUN Z X, LI B. Sketch retrieval based on spatial relations ［A］ . Pr oceedings of International Conference on Computer Graphics, Imaging and Visualiz ation (cgiv05)［C］. Beijing, China, 2005.
Similar References:

Memo

-

Last Update: 2009-05-07

Copyright © CAAI Transactions on Intelligent Systems