Abstract
This paper proposes an image filtering and retrieval system driven by the multi-instance learning (MIL) algorithm. This system is aimed at improving the mission effectiveness of human analysts in searching through imagery for environmental, defense, or other purposes. Thus, the system is tuned and the experimental results are measured in terms of the true positive rate in predicted labels. While MIL has been used in image retrieval before, this paper examines how different tasks and feature spaces impact the performance of the algorithm. Images are translated into the single blob with neighbors (SBN) feature space, a novel feature space called color, texture, and shape (CTS), and a combined SBN and CTS feature space, for processing by the MIL algorithm. The paper introduces a feature space selection step in the classification process and shows that the true positive rate can be increased through the addition of this step.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Anderson K, Gaston KJ (2013) Lightweight unmanned aerial vehicles will revolutionize spatial ecology. Front Ecol Environ 11(3):138–146
Andrews S, Hofmann T, Tsochantaridis I (2002) Multiple instance learning with generalized support vector machines. In: AAAI/IAAI, pp 943–944
Chevaleyre Y, Zucker JD (2000) Noise-tolerant rule induction from multi-instance data. In: ICML 2000, workshop on attribute-value and relational learning
Dietterich TG, Lathrop RH, Lozano-Pérez T (1997) Solving the multiple instance problem with axis-parallel rectangles. Artif Intell 89(1–2):31–71. doi:10.1016/S0004-3702(96)00034-3
Kim K, Owechko Y, Flores A, Korchev D (2011) Multisensor ISR in geo-registered contextual visual dataspace (cvd). In: Society of Photo-Optical Instrumentation Engineers (SPIE) conference series, vol 8049, p 20
Maron O, Lozano-Prez T (1998) A framework for multiple-instance learning. In: Advances in neural information processing systems. MIT Press, pp 570–576
Maron O, Ratan AL (1998) Multiple-instance learning for natural scene classification. In: In the fifteenth international conference on machine learning. Morgan Kaufmann, pp 341–349
Nisbet R, Elder J IV, Miner G (2009) Handbook of statistical analysis and data mining applications. Academic Press, London
Peters J (2014) Texture and texture set patterns. In: Topology of digital images, intelligent systems reference library, vol 63. Springer, Berlin, pp 301–315
Qiao Q, Beling PA (2009) Localized content based image retrieval with self-taught multiple instance learning. In: ICDM Workshops, pp 170–175
Tong S, Chang E (2001) Support vector machine active learning for image retrieval. In: Proceedings of the ninth ACM international conference on multimedia, ACM, New York, NY, USA, MULTIMEDIA ’01, pp 107–118. doi:10.1145/500141.500159
Touryan J, Gibson L, Horne J, Weber P (2010) Real-time classification of neural signals corresponding to the detection of targets in video imagery. CRC Press, pp 190–199. doi:10.1201/EBK1439835012-c19
Touryan J, Gibson L, Horne JH, Weber P (2011) Real-time measurement of face recognition in rapid serial visual presentation. Front Psychol 2
Wang J (2000) Solving the multiple-instance problem: a lazy learning approach. In: Proceedings 17th international conference on machine learning. Morgan Kaufmann, pp 1119–1125
Yang C, Lozano-Perez T (2000) Image database retrieval with multiple-instance learning techniques. In: Proceedings 16th international conference on data engineering, 2000, pp 233–243. doi:10.1109/ICDE.2000.839416
Zhou Z, Zhang M (2007) Multi-instance multilabel learning with application to scene classification. Adv Neural Inf Process Syst 19
Acknowledgments
The authors would like to thank Laurie Gibson, Chief Scientist, SAIC Inc. for her gracious help with the human subject experiment and her advice regarding this paper. The first author gratefully acknowledges support from an SAIC Graduate Fellowship at the University of Virginia. This material is based upon work supported by the National Science Foundation under Grant No. EEC-0827153.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Birisan, M., Beling, P.A. A multi-instance learning approach to filtering images for presentation to analysts. Environ Syst Decis 34, 406–416 (2014). https://doi.org/10.1007/s10669-014-9512-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10669-014-9512-7