Abstract
Consider a set-classification task where c objects must be labelled simultaneously in c classes, knowing that there is only one object coming from each class (full-class set). Such problems may occur in automatic attendance registration systems, simultaneous tracking of fast moving objects and more. A Bayes-optimal solution to the full-class set classification problem is proposed using a single classifier and the Hungarian assignment algorithm. The advantage of set classification over individually based classification is demonstrated both theoretically and experimentally, using simulated, benchmark and real data.
Similar content being viewed by others
Notes
The relevance of the logarithm will transpire later in relation to the Bayes optimality of the set classifier. The base of the logarithm can be any.
The Matlab code for the Hungarian algorithm was written by Alex Melin, University of Tennessee, 2006, available through Matlab Central.
References
Amit Y, Trouvé A (2007) POP: patchwork of parts models for object recognition. Int J Comput Vis 75:267–282
Asuncion A, Newman DJ (2007) UCI machine learning repository. University of California, Irvine, School of Information and Computer Sciences. http://www.ics.uci.edu/~mlearn/MLRepository.html
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Analy Mach Intell 24:509–522
Dietterich TG, Lathrop RH, Lozano-Perez T (1997) Solving the multiple-instance problem with axis-parallel rectangles. Artif Intell 89:31–71
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, NY
Fawcett T (2003) ROC graphs: notes and practical considerations for researchers. Technical Report HPL-2003-4, HP Labs, Palo Alto. http://www.hpl.hp.com/techreports/2003/HPL-2003-4.pdf
Hand DJ (2006) Classifier technology and the illusion of progress (with discussion). Stat Sci 21:1–34
Kaucic R, Perera AGA, Brooksby G, Kaufhold J, Hoogs A (2005) A unified framework for tracking through occlusions and across sensor gaps. In: IEEE computer society conference on computer vision and pattern recognition, CVPR, vol 1, pp 1063–1069
Kuhn HW (1955) The Hungarian method for the assignment problem. Nav Res Logist Q 2:83–97
Kuncheva LI (2002) A theoretical study on expert fusion strategies. IEEE Trans Pattern Anal Mach Intell 24(2):281–286
Mangasarian OL, Wild EW (2008) Multiple instance classification via successive linear programming. J Optim Theory Appl 137:555–568
McDowell LK, Gupta KM, Aha DW (2007) Cautious inference in collective classification. In: Processdings of AAAI, pp 596–601
Ning X, Karypis G (2009) The set classification problem and solution methods. In: Proceedings of SIAM data mining, pp 847–858
Provost F, Domingos P (2003) Tree induction for probability-based ranking. Mach Learn 52(3):199–215
Ripley BD (1996) Pattern recognition and neural networks. University Press, Cambridge
Sen P, Namata G, Bilgic M, Getoor L, Gallagher B, Eliassi-Rad T (2008) Collective classification in network data. AI Magazine 29:93–106
Wang J, Zucker J-Dl (2000) Solving the multiple-instance problem: a lazy learning approach. In: Proceedings 17th international conference on machine learning, pp 1119–1125
Zadrozny B, Elkan C (2001) Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers. In: Proceedings of the eighteenth international conference on machine learning (ICML’01), pp 609–616
Zadrozny B, Elkan C (2002) Transforming classifier scores into accurate multiclass probability estimates. In: Proceedings of the 8th international conference on knowledge discovery and data mining (KDD’02)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kuncheva, L.I. Full-class set classification using the Hungarian algorithm. Int. J. Mach. Learn. & Cyber. 1, 53–61 (2010). https://doi.org/10.1007/s13042-010-0002-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-010-0002-z