Abstract
Automatic content-based image categorization is a challenging research topic and has many practical applications. Images are usually represented as bags of feature vectors, and the categorization problem is studied in the Multiple-Instance Learning (MIL) framework. In this paper, we propose a novel learning technique which transforms the MIL problem into a standard supervised learning problem by defining a feature vector for each image bag. Specifically, the feature vectors of the image bags are grouped into clusters and each cluster is given a label. Using these labels, each instance of an image bag can be replaced by a corresponding label to obtain a bag of cluster labels. Data mining can then be employed to uncover common label patterns for each image category. These label patterns are converted into bags of feature vectors; and they are used to transform each image bag in the data set into a feature vector such that each vector element is the distance of the image bag to a distinct pattern bag. With this new image representation, standard supervised learning algorithms can be applied to classify the images into the pre-defined categories. Our experimental results demonstrate the superiority of the proposed technique in categorization accuracy as compared to state-of-the-art methods.
Similar content being viewed by others
References
Andrews S, Tsochantaridis I, Hofmann T (2002) Support vector machine for multiple-instance learning. In: NIPS ’02: advances in neural information processing systems. MIT, Cambridge, pp 561–568
Bakar ZA, Mohemad R, Ahmad A (2006) A comparative study for outlier detection techniques in data mining. In: CIS ’06: IEEE conference on cybernetics and intelligent systems. IEEE, New York, pp 1–6
Bay SD, Schwabacher M (2003) Mining distance-based outliers in near linear time with randomization and a simple pruning rule. In: KDD ’03: proceedings of the ninth ACM SIGKDD international conference on knowledge discovery and data mining. ACM, New York, pp 29–38
Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York
Borgelt C, Kruse R (2002) Induction of association rules: apriori implementation. In: COMPSTAT ’02: 15th conference on computational statistics, Berlin, Germany, pp 1–6 (Online publication)
Burdick D, Calimlim M, Gehrke J (2001) Mafia: a maximal frequent itemset algorithm for transactional databases. In: ICDE ’01: proceedings of the 17th international conference on data engineering. IEEE Computer Society, Washington, DC, pp 443–452
Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Mining Knowledge Discovery 2(2):121–167
Chang C, Lin C (2001) LIBSVM: a library for support vector machines.
Cheng H, Hua KA (2009) Similarity search in point-set databases. Technical report, School of Eletrical Engineering and Computer Science, University of Central Florida
Chen Y, Wang JZ (2004) Image categorization by learning and reasoning with regions. J Mach Learn Res 5(2):913–939
Chen Y, Bi J, Wang JZ (2006) Miles: multiple-instance learning via embedded instance selection. IEEE Trans Pattern Anal Mach Intell 28(12):1931–1947
Chen X, Zhang C, Chen S-C, Chen M (2005) A latent semantic indexing based method for solving multiple instance learning problem in region-based image retrieval. In: ISM ’05: seventh IEEE international symposium on multimedia. IEEE Computer Society, Washington, pp 37–45
Cheng H, Hua KA, Vu K (2007) Local and global structures preserving projection. In: ICTAI ’07: proceedings of the 19th IEEE international conference on tools with artificial intelligence. IEEE Computer Society, Washington, DC, pp 362–365
Csurka G, Dance CR, Fan L, Willamowski J, Bray C (2004) Visual categorization with bags of keypoints. In: SLCV ’04: proceedings of ECCV international workshop on statistical learning in computer vision, Prague, Czech Republic, pp 1–22 (Online publication)
Deselaers T, Keysers D, Ney H (2008) Features for image retrieval: an experimental comparison. Inf Retrieval 11(2):77–107
Dooly DR, Zhang Q, Goldman SA, Amar RA (2003) Multiple instance learning of real valued data. J Mach Learn Res 3(1):651–678
Hamerly G, Elkan C (2003) Learning the k in K-Means. In: NIPS ’03: advances in neural information processing systems, vol 16. MIT, Cambridge, p 36
Maron O, Ratan AL (1998) Multiple-instance learning for natural scene classification. In: ICML ’98: proceedings of the fifteenth international conference on machine learning. Morgan Kaufmann, San Francisco, pp 341–349
Mikolajczyk K, Schmid C (2005) A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 27(10):1615–1630
Moore DS, McCabe GP (1993) Introduction to the practice of statistics. Freeman, New York
Schrijver A (1986) Theory of linear and integer programming. Wiley, New York
Shekhar S, Lu C-T, Zhang P (2003) A unified approach to detecting spatial outliers. Geoinformatica 7(2):139–166
Vu K, Hua KA, Cheng H, Lang S-D (2006) A non-linear dimensionality-reduction technique for fast similarity search in large databases. In: SIGMOD ’06: proceedings of the 2006 ACM SIGMOD international conference on management of data. ACM, New York, pp 527–538
Wang J, Zucker J-D (2000) Solving the multiple-instance problem: a lazy learning approach. In: ICML ’00: proceedings of the seventeenth international conference on machine learning. Morgan Kaufmann, San Francisco, pp 1119–1126
Zhang Q, Goldman S (2001) EM-DD: an improved multiple-instance learning technique. In: NIPS ’01: neural information processing systems, vol 14. MIT, Cambridge, pp 1073–1080
Zhou Z-H, Xu J-M (2007) On the relation between multi-instance learning and semi-supervised learning. In: ICML ’07: proceedings of the 24th international conference on machine learning. ACM, New York, pp 1167–1174
Author information
Authors and Affiliations
Corresponding author
Appendix: Proof of convergence of Algorithm 1
Appendix: Proof of convergence of Algorithm 1
In this section, we would like to prove the correctness of Algorithm 1. The problem to be solved is to find an optimal vector \(\vec{v}^{j, c_i}\) satisfying,
in which, \(\mathcal{Y}^{j, c_i}\) is a set of bags with regard to cluster c i and category j.
For a vector \(\vec{v}\), and a mapping function \(\mathit \Upsilon\), denote \(\mathit \Upsilon(Y^{j, c_i}_k)\) to be the instance from the bag \(Y^{j, c_i}_k\) which is mapped to vector \(\vec{v}\). Therefore the optimal \(\vec{v}^{j, c_i}\) also achieves the below optimization problem,
Therefore, we would like to find a vector to minimize
For a fixed vector \(\vec{v}\), the optimal mapping of each bag \(Y^{j, c_i}_k\) is to map \(\vec{v}\) to the closest one among all the instances in \(Y^{j, c_i}_k\), i.e.,
For a fixed mapping \(\mathit \Upsilon\), the optimal vector is the centers of all the matched instances, i.e.,
Algorithm 1 takes the iterative approach to reach a local minimum of the objective function defined in Eq. 1. It starts with an initial guess of the vector. Each run of Step 2 of the algorithm is to find the matched instances with regard to the current vector. This guarantees to reduce the objective. In Step 3, the vector to be computed is updated as the centroid of the matched instances, which certainly decreases the objective value. Therefore Algorithm 1 is sure to have the objective value smaller and smaller. Because there are only a finite number of instances in \(\mathcal{Y}^{j, c_i}\), there only exists a finite number of mapping, and the objective function defined in Eq. 1 is lower-bounded. Overall, Algorithm 1 guarantees to converge and the derived optimal vector gives a local minimum of the objective function.
Rights and permissions
About this article
Cite this article
Cheng, H., Hua, K.A. & Yu, N. An automatic feature generation approach to multiple instance learning and its applications to image databases. Multimed Tools Appl 47, 507–524 (2010). https://doi.org/10.1007/s11042-009-0335-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-009-0335-3