90
91
gereken bir baĢka çalıĢmadır. Böyle bir çalıĢmanın yapılması bu tür bir araĢtırmada en iyi performans ölçütünün seçilmesi aĢamasında bir fikir verecektir.
ÇalıĢmada elde edilen bulgular sabit olmasına rağmen insanların gruplandırma seçimlerine bağlı olarak performans ölçütleri üzerinde kiĢiden kiĢiye büyük değiĢimlerin olduğu gözlemlenmiĢtir. Bu tür bir öngörü çalıĢmaya baĢlarken de göz önüne alınmıĢ ve çalıĢmanın sonunda ulaĢılan bulgular da bunu desteklemiĢtir. Problemi zorlaĢtıran ana nokta da zaten kiĢiye bağlı olma özelliğidir. Ġnsanlarla algoritma arasındaki bu bağı kırmak ve performans ölçütlerinin kiĢiye bağlılığını azaltmak için uygulanabilecek bir yöntem, kiĢilere gruplandırma yaptırmak yerine algoritmanın oluĢturduğu her gruptaki elemanlara kiĢiler tarafından bir not verilmesi ve bu verilen notlar üzerinden benzer yapıda bir performans ölçütünün oluĢturulması olabilir. Fakat, bu konuda bir çalıĢma yapılmadığı sürece bu yeni performans ölçütünün baĢarımı bir yorum yapmak çok da doğru olmayacaktır.
TartıĢılması gereken bir baĢka konu da bu yöntemin nerelerde kullanılabileceğidir. Buna bir örnek olarak Ģöyle bir senaryo düĢünülebilir. Google™ imge arama motoru imgeleri ararken daha önce de belirtildiği gibi imgenin içeriğine bakmak yerine dosya ismi, meta verisi gibi yazı tabanlı bilgilere dayanmaktadır. Google™ üzerinden bulunan imgelerin bu tür bir algoritmaya sokularak gruplandırılmasından elde edilen sonuçlar bir ara basamak olarak kullanıcıya verildiğinde kullanıcının ihtiyaçlarına daha uygun bir yöne yönelmesi arama motoru tarafından sağlanmıĢ olacaktır. ÇalıĢmanın bu aĢamasında bu tür bir iĢbirliğinin yapılması mümkün olmasa da bu yönde yapılan çalıĢmaların artması ve elde edilen baĢarımların artmasıyla internet arama motorları da içerik tabanlı arama yöntemlerine yönelecektir.
Sakarya ve Telatar (2008) benzer bir çalıĢmayı video görüntüleri üzerinde yaparak dikkat çekici bir Ģekilde oldukça baĢarılı sonuçlar elde etmiĢtir. Bu baĢarıların elde edilmesindeki en önemli etken video görüntülerinin kendi içinde sahneden sahneye çok ilintili olmasıdır. Bu çalıĢmada masaüstü imgelerin gruplandırılması amacıyla kullanılan Ġstanbul konulu imge kümesi de benzer bir Ģekilde kendi içinde oldukça ilintili imgeler içerdiği için baĢarılı sonuçlar vermiĢtir. Bununla birlikte kullanılan diğer imge kümeleri
92
internet üzerinden indirildiği ve aralarındaki ilinti çok düĢük olduğu için görece daha baĢarısız sonuçlar vermektedir. Çok daha fazla sayıda imgeler içeren imge kümelerinin kullanılması durumunda artan imge sayısına bağlı olarak ilintili imgelerin sayısı da artacağı için baĢarımın artacağı söylenebilir.
Sonuç olarak, problemin zorluğu da göz önüne alınarak baĢarılı sonuçların elde edildiği düĢünülmektedir. TartıĢıldığı üzere bu çalıĢma aynı zamanda bu yönde yapılacak çalıĢmalara bir örnek teĢkil etmekte ve bu alanda yapılması gereken bazı geliĢtirmeler konusunda da bir fikir vermektedir.
93 KAYNAKLAR
Aksoy, S. and Haralick, R.M. 1998. Textural features for image database retrieval.
Proceedings of IEEE Workshop on Content-Based Access of Image and Video Libraries, 45-49, Seattle, WA.
Aksoy, S. and Haralick, R.M. 1999. Graph-theoretic clustering for image grouping and retrieval. Proceedings of the 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR‟99), 1, 63-68.
Anonim. 2008. Görüntü aramaları için Google sıkça sorulan sorular.
http://www.google.com.tr/intl/tr/help/faq_images.html. EriĢim Tarihi:
28.12.2008
Anderberg, M.R. 1973. Cluster analysis for applications. Academic Press, Inc., New York.
Auguston, J.G. and Minker, J. 1970. An analysis of some graph theoretical clustering techniques, J. ACM, 17(4), 571-588.
Ball, G.H. and Hall, D.J. 1964. Some fundamental concepts and synthesis procedures for pattern recognition preprocessors. International Conference on Microwaves, Circuit Theory, and Information Theory, September, Tokyo.
Barnard, K., Duygulu, P. and Forsyth, D. 2001. Clustering art. Computer Vision and Pattern Recognition, 2, 434-439.
Barnard, K., Duygulu, P., Forsyth, D., De Freitas, N., Blei, D.M. and Jordan, M.I. 2003.
Matching words and pictures. Journal of Machine Learning Research, 3, 1107-1135.
Ben Haim, N., Babenko, B. and Belongie, S.J. 2006. Improving web-based image search via content based clustering. SLAM‟06, 106-111.
Bomze, I.M. 1997. Evolution towards the maximum clique. Journal of Global Optimization, 10, 143-164.
Carson, C., Thomas, M., Belongie, S., Hellerstein, J. M. and Malik, J. 1999.
Blobworld: a system for region-based image indexing and retrieval. In Third International Conference on Visual Information Systems, Springer, 509-516.
Cha, S.H. and Srihari, S.N. 2002. On measuring the distance between histograms. In Pattern Recognition, 35(6), 1355-1370.
94
Cha, S.H. 2008. Taxonomy of nominal type histogram distance measures. In Proceedings of the American Conference on Applied Mathematics (MATH ‟08), 325-330.
Charikar, M. 2000. Greedy approximation algorithms for finding dense components in a graph. Proceedings of APPROX, Springer Berlin / Heidelberg, 1912/2000, 139-152.
Chen, Y., Wang, J.Z. and Provetz, R. 2005. CLUE: cluster-based retrieval of images by unsupervised learning. IEEE Transactions on Image Processing, 14(8), 1187-1201.
Cheng, Y. 1995. Mean shift, mode seeking, and clustering. IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(8), 790-799.
Christofides, N. 1975. Graph theory: an algorithmic approach. Academic Press, 400 p., London.
Clifford, H.T. and Stephenson, W. 1975. An introduction to numerical classification.
Academic Press, Inc., New York.
Comaniciu, D. 2002. Image segmentation using clustering with saddle point detection.
Proceedings of the 2002 International Conference on Image Processing (ICIP‟02), 3, 297-300.
Deselaers, T., Keysers, D., and Ney, H. 2003. Clustering visually similar images to improve image search engines. Informatiktage der Gesellschaft für Informatik, Springer, 302-305.
Deza, E. and Deza, M.M. 2006. Dictionary of distances, Elsevier.
Drineas, P., Frieze, A., Kannan, R., Vempala, S. and Vinay, V. 1999. Clustering in large graphs and matrices. Proceedings of 10th Symposium on Discrete Algorithms, 291-299.
Dubnov, S., El-Yaniv., R., Gdalyahu, Y., Schneidman, E., Tishby, N. and Yona, G.
2002. A new nonparametric pairwise clustering algorithm based on iterative estimation of distance profiles. Machine Learning, Academic Publishers, 47, 35-61.
Duda, R.O, Hart, P.E. and Stork, D.G. 2001. Pattern classification, 2nd ed., Wiley.
Dubes, R. and Jain, A.K. 1976. Clustering techniques: the user‟s dilemma. Pattern Recognition, 8, 247-260.
95
Dubes, R. and Jain, A.K. 1980. Clustering methodologies in exploratory data analysis.
In Advances in Computers (M.C. Yovitz, ed.), Academic Press, Inc., 19, 113-215, New York.
Edwards, A.W.F. and Cavalli-Sforza, L.L. 1965. A method for cluster analysis.
Biometrics, 21, 362-375.
Everitt, B.S. and Nicholls, P. 1975. Visual techniques for representing multivariate data.
The Statistician, 24, 37-49.
Felzenszwalb, P.F. and Huttenlocher, D.P. 2004. Efficient graph-based image segmentation. International Journal of Computer Vision, Springer, 59(2), 167-181.
Fergus, R., Perona, P. and Zisserman, A. 2004. A visual category filter for google images. In Proc. ECCV, Springer-Verlag, 242-256.
Fergus, R., Fei-fei, L., Perona, P. and Zisserman, A. 2005. Learning object categories from google‟s image search. Proceedings of the 9th International Conference on Computer Vision (ICCV‟05), 1816-1823.
Forgy, E. 1965. Cluster analysis of multivariate data: efficiency versus interpretability of classifications. In Biometrics, 21, 768 (Abstract).
Fortier, J.J. and Solomon, H. 1966. Clustering procedures. In Multivariate Analysis (P.R. Krishnaiah, ed.), Academic Press, Inc., 493-506, New York.
Fraley, C. and Raftery, A. E. 1998. How many clusters? Which clustering method?
Answers via model-based cluster analysis. The Computer Journal, 41, 578-588.
Friedman, J.H. and Rafsky, L.C. 1981. Graphics for the multivariate two-sample problem. Journal of the American Statistical Association, 76, 277-287.
Frieze, A.M. 1980. Probability analysis of some euclidian clustering problems. Discrete Applied Mathematics, 2, 295-309.
Gavin, D.G., Oswald, W.W., Wahl, E.R. and Williams, J.W. 2003. A statistical approach to evaluating distance metrics and analog assignments for pollen records, Quaternary Research, 60, 356-367.
Gdalyahu, Y. and Weinshall, D. 1999. Flexible syntactic matching of curves and its application to automatic hierarchical classification of silhouettes. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(12), 1312-1328.
96
Gdalyahu, Y., Weinshall, D. and Werman, M. 2001. Self-organization in region:
stochastic clustering for image segmentation, perceptual grouping, and image database organization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(10), 1053-1074.
Gordon, A.D. and Henderson, J.T. 1977. Algorithm for euclidian sum of squares classification. In Biometrics, 33, 355-362.
Gowda, K.C. and Krishna, G. 1978. Agglomerative clustering using the concept of mutual nearest neighborhood. Pattern Recognition, 10, 105-112.
Hafner, J., Sawhney, H.S., Equitz, W., Flickner, M. and Niblack, W. 1995. Efficient color histogram indexing for quadratic form distance functions. IEEE Transaction on Pattern Analysis and Machine Intelligence, 17(7), 729-736.
Hlaoui, A. and Wang, S. 2003. A graph clustering algorithm with applications to content-based image retrieval. Proceedings of the Second International Conference on Machine Learning and Cybernetics, 1855-1861.
Hubert, L.J. 1974. Some applications of graph theory to clustering. Psychometrika, 38, 435- 475.
Jain, A.K. and Dubes, R.C. 1988. Algorithms for clustering data. Prentice Hall, 320 p., Englewood Cliffs, New Jersey.
Jensen, R.E. 1969. A dynamic programming algorithm for cluster analysis. Operations Research, 17, 1034-1057.
Kendall, M.G. 1966. Discrimination and classification. In Multivariate Analysis (P.R.
Krishnaiah, ed.), Academic Press, Inc., pp. 165-185, New York
Kittler, J. 1976. A locally sensitive method for cluster analysis. Pattern Recognition, 8, 22-23.
Kleiner, B. and Hartigan, J.A. 1981. Representing points in many dimensions by trees and castles. Journal of the American Statistical Association, 76, 260-269.
Koontz, W.L.G., Narendra, P.M. and Fukunaga, K. 1975. A branch and bound clustering algorithm. IEEE Transactions on Computers, C-23, 908-914.
Koontz, W.L.G., Narendra, P.M. and Fukunaga, K. 1976. A graph-theoretic approach to nonparametric cluster analysis. IEEE Transactions on Computers, C-25(9), 936-944.
97
Lance, G.N. and Williams, W.T. 1967. A general theory of classificatory sorting strategies: II, Clustering systems. Computer Journal, 10, 271-277.
Lefkovitch, L.P. 1980. Conditional clustering. Biometrics, 36, 43-58.
Luo, B., Robles Kelly, A., Torsello, A., Wilson, R.C. and Hancock, E.R. 2001. A probabilistic framework for graph clustering. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR‟01), 1, 912-919.
Matula, D.W. 1977. Graph theoretic techniques for cluster analysis algorithms. In Classification and Clustering (J. Van Ryzin, ed.), Academic Press, Inc., 95-129, New York.
McQueen, J.B. 1967. Some methods of classification and analysis of multivariate observations. Proceedings of Fifth Berkeley Symposium on Mathematical Statistics and Probability, 281-297.
Monev, V. 2004. Introduction to similarity searchin in chemistry, MATCH Commun.
Math. Comput. Chem., 51, 7-38.
Özkan, D. and Duygulu, P. 2006. A graph based approach for naming faces in news photos. Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR‟06), 2, 1477-1482.
Pavan, M. and Pelillo, M. 2003a. A new graph-theoretic approach to clustering and segmentation. Proceedings of the 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR‟03), 1, 145-152.
Pavan, M. and Pelillo, M. 2003b. Unsupervised texture segmentation by dominant sets and game dynamics. Proceedings of the 12th International Conference on Image Analysis and Processing (ICIAP‟03), 302-307.
Pavan, M. and Pelillo, M. 2003c. Dominant sets and hierarchical clustering.
Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV‟03), 1, 362-369.
Pavan, M. 2004. A new graph-theoretic approach to clustering, with applications to computer vision. Ph.D. thesis, Università di Bologna, Padova, Venezia, 112 p., Italy.
98
Pavan, M. and Pelillo, M. 2005. Efficient out-of-sample extension of dominant-set clusters: advances in neural information processing systems, in: L.K. Saul, Y.
Weiss, L. Bottou (Eds.), 17, 1057-1064.
Pavan, M. and Pelillo, M. 2007. Dominant sets and pairwise clustering. IEEE Trans. on Pattern Analysis and Machine Intelligence, 29(1), 167-172.
Pelillo, M., Siddiqi, K. and Zucker, S.W. 1999. Matching hierarchical structures using association graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 21(11), 1105-1119.
Pelillo, M. 2006. Clustering and image segmentation. Primo Workshop Annuale del Dipartimento di Informatica Università Ca' Foscari di Venezia, Italy.
Peng, Y. and Ngo, C.W. 2006. Clip-based similarity measure for querydependent clip retrieval and video summarization. IEEE Trans. Circuit Syst. Video Technol., 16, 612-627.
Perona, P. and Freeman, W. 1998. A factorization approach to grouping. In Computer Vision – ECCV‟98 (H. Burkhardt and B. Neumann, ed.), Springer-Verlag, 655-670, Berlin.
Raghavan, V.V. and Yu, C.T. 1981. A comparison of the stability characteristics of some graph theoretic clustering methods, IEEE Transactions on Pattern Analysis Machine Intelligence, 3, 393-402.
Rao, M.R. 1971. Cluster analysis and mathematical programming. Journal of the American Statistical Association, 66, 622-626.
Sarkar, S. and Boyer, K.L. 1998. Quantitative measures of change based on feature organization: Eigenvalues and eigenvectors. Computer Vision and Image Understanding, 71(1), 110-136.
Sakarya, U. and Telatar, Z. 2008. Graph-based multilevel temporal video segmentation.
Multimedia Systems, Springer Berlin / Heidelberg, 14(5), 277-290.
Schroff, F., Criminisi, A. and Zisserman, A. 2007. Harvesting image databases from the web.
Proceedings of the 11th International Conference on Computer Vision (ICCV‟07), 1-8.
Selim, S.Z. and Ismail, M.A. 1984. K-means-type algorithms: a generalized convergence theorem and characterization of local optimality. IEEE Trans. On Pattern Analysis and Machine Intelligence PAMI, 6, 81-87.
99
Sevil, S., Zitouni, H., Ġkizler, N., Özkan, D. ve Duygulu, P. 2008. Resim arama sonuçlarının çizge tabanlı bir yöntemle yeniden sıralanması. IEEE 16. Sinyal ĠĢleme, ĠletiĢim ve Uygulamaları Kurultayı (SIU 2008), Didim, Türkiye.
Shaffer, E., Dubes, R. and Jain, A.K. 1979. Single-link characteristics of a mode-seeking algorithm. Pattern Recognition, 11, 81-87.
Shepard, R.N. and Arabie, P. 1979. Additive clustering: representation of similarities as combinations of discrete overlapping properties. Psychological Review, 86, 87-123.
Shi, J. and Malik, J. 2000. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(8), 888-905.
Sneath, P.H.A. and Sokal, R.R. 1973. Numerical Taxonomy, W.H. Freeman and Company, Publishers, San Francisco.
Tzerpos, V. and Holt, R. C. 2000. On the stability of software clustering algorithms. In Proceedings of the 8th International Workshop on Program Comprehension, 211-218.
Urquhart, R. 1982. Graph theoretical clustering based on limited neighborhood sets.
Pattern Recognition, 15, 173-187.
Vinod, H.D. 1969. Integer programming and theory of grouping. Journal of the American Statistical Association, 64, 506-519.
Wu, Z. and Leahy, R. 1993. An optimal graph theoretic approach to data clustering:
theory and its application to image segmentation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 15(11), 1101-1113.
Zahn, C.T. 1971. Graph-theoretical methods for detecting and describing gestalt clusters. IEEE Transactions of Computers, C-20(1), 68-86.
Zezula, P., Amato, G., Dohnal, V. and Batko, M. 2006. Similarity search the metric space approach, Springer.
Zhai, Y. and Shah, M. 2006. Video scene segmentation using Markov chain Monte Carlo. IEEE Trans. Multimedia, 8, 686-697.