Abstract
Most existing content-based image retrieval and classification systems rely on low-level features which are automatically extracted from images. However, often these features lack the discrimination power needed for accurate description of the image content, and hence, they may lead to a poor retrieval or classification performance. We propose a novel technique to improve low-level features which uses parallel one-against-all perceptrons to synthesize new features with a higher discrimination power which in turn leads to improved classification and retrieval results. The proposed method can be applied on any database and low-level features as long as some ground-truth information is available. The main merits of the proposed technique are its simplicity and faster computation compared to existing feature synthesis methods. Extensive simulation results show a significant improvement in the features’ discrimination power.
Similar content being viewed by others
References
Bäck T, Schwefel HP (1993) An overview of evolutionary algorithms for parameter optimization. Evolut. Comput. 1(1):1–23. doi:10.1162/evco.1993.1.1.1
Bergamo A, Torresani L, Fitzgibbon A (2011) Picodes: learning a compact code for novel-category recognition. In: Shawe-Taylor J, Zemel R, Bartlett P, Pereira F, Weinberger K (eds) Advances in neural information processing systems 24, pp 2088–2096
Bhanu B, Yu J, Tan X, Lin Y (2004) Feature synthesis using genetic programming for face expression recognition. In: Proceedings of genetic and evolutionary computation conference, Part II, Seattle, pp 896–907. doi:10.1007/978-3-540-24855-2_103
Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27:1–27:27. doi:10.1145/1961189.1961199
Chua TS, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) Nus-wide: a real-world web image database from national university of Singapore. In: Proceedings of the ACM international conference on image and video retrieval, ACM, New York, pp 48:1–48:9. doi:10.1145/1646396.1646452
Daskalaki S, Kopanas I, Avouris N (2006) Evaluation of classifiers for an uneven class distribution problem. Appl Artif Intel 20:1–37. doi:10.1080/08839510500313653
Dong A, Bhanu B, Lin Y (2005) Evolutionary feature synthesis for image databases. In: Proceedings of 7th IEEE workshop on application of computer vision, vol 1, pp 330–335. doi:10.1109ACVMOT.2005.50
Fei-Fei L, Fergus R, Perona P (2007) Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59–70. doi:10.1016/j.cviu.2005.09.012
Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning, 1st edn. Addison-Wesley Longman Publishing Co. Inc, Boston
Jiang YG, Wang J, Xue X, Chang SF (2013) Query-adaptive image search with hash codes. IEEE Trans Multimed 15(2):442–453. doi:10.1109/TMM.2012.2231061
Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of the IEEE international conference on neural networks, vol 4, pp 1942–1948. doi:10.1109/ICNN.1995.488968
Kiranyaz S, Ince T, Yildirim A, Gabbouj M (2009) Evolutionary artificial neural networks by multi-dimensional particle swarm optimization. Neural Netw 22(10):1448–1462. doi:10.1016/j.neunet.2009.05.013
Kiranyaz S, Ince T, Yildirim A, Gabbouj M (2010) Fractional particle swarm optimization in multidimensional search space. IEEE Trans Syst Man Cybern Part B Cybern 40(2):298–319. doi:10.1109/TSMCB.2009.2015054
Kiranyaz S, Pulkkinen J, Ince T, Gabbouj M (2011a) Multi-dimensional evolutionary feature synthesis for content-based image retrieval. In: Proceedings of 18th IEEE international conference on image processing, Brussels, pp 3645–3648. doi:10.1109/ICIP.2011.6116508
Kiranyaz S, Uhlmann S, Pulkkinen J, Gabbouj M, Ince T (2011b) Collective network of evolutionary binary classifiers for content-based image retrieval. In: Proceedings of IEEE workshop on evolving and adaptive intelligent systems, Paris, pp 147–154. doi:10.1109/EAIS.2011.5945925
Kiranyaz S, Ince T, Uhlmann S, Gabbouj M (2012) Collective network of binary classifier framework for polarimetric sar image classification: an evolutionary approach. IEEE Trans Syst Man Cybern Part B Cybern 42(4):1169–1186. doi:10.1109/TSMCB.2012.2187891
Kiranyaz S, Ince T, Gabbouj M (2014) Multidimensional particle swarm optimization for machine learning and pattern recognition. Springer, NewYork
Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge
Li P, Wang M, Cheng J, Xu C, Lu H (2013) Spectral hashing with semantically consistent graph for image indexing. IEEE Trans Multimed 15(1):141–152. doi:10.1109/TMM.2012.2199970
Li R, Bhanu B, Dong A (2005) Coevolutionary feature synthesized em algorithm for image retrieval. In: Proceedings of the 13th annual ACM international conference on multimedia, ACM, New York, pp 696–705. doi:10.1145/1101149.1101304
Li R, Bhanu B, Dong A (2008) Feature synthesized em algorithm for image retrieval. ACM Trans Multimed Comput Commun Appl 4(2):10:1–10:24. doi:10.1145/1352012.1352014
Lin Y, Bhanu B (2005) Evolutionary feature synthesis for object recognition. IEEE Trans Syst Man Cybern Part C Appl Rev 35(2):156–171. doi:10.1109/TSMCC.2004.841912
Mäkinen T, Kiranyaz S, Raitoharju J, Gabbouj M (2012) An evolutionary feature synthesis approach for content-based audio retrieval. EURASIP J Audio Speech Music Process 2012(23):1–23. doi:10.1186/1687-4722-2012-23
Manjunath B, Salembier P, Sikora T (2002) Introduction to MPEG-7. Wiley, San Francisco
Mittelman R, Lee H, Kuipers B, Savarese S (2013) Weakly supervised learning of mid-level features with beta-bernoulli process restricted boltzmann machines. In: Proceedings of IEEE conference on computer vision and pattern recognition, pp 476–483. doi:10.1109/CVPR.2013.68
Torresani L, Szummer M, Fitzgibbon A (2010) Efficient object category recognition using classemes. In: Proceedings of 11th European conference on computer vision, Part I, Heraklion, pp 776–789
Yu J, Bhanu B (2006) Evolutionary feature synthesis for facial expression recognition. Pattern Recognit Lett 27(11):1289–1298. doi:10.1016/j.patrec.2005.07.026
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Raitoharju, J., Kiranyaz, S. & Gabbouj, M. Feature synthesis for image classification and retrieval via one-against-all perceptrons. Neural Comput & Applic 29, 943–957 (2018). https://doi.org/10.1007/s00521-016-2504-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2504-4