International Journal of Mathematics Trends and Technology
Volume 53 | Number 6 | Year 2018 | Article Id. IJMTT-V53P559 | DOI : https://doi.org/10.14445/22315373/IJMTT-V53P559
A dictionary of template is a key semantic component in a hierarchical sparse method (HSM). Since template selection attempts to eliminate redundant and irrelevant template, successful extract sucient templates will lead to more discriminative ability of the HSM. In this paper, we present development of HSM by introduce a new template selection method based on the entropy concept. Its a way to indicate the total information the templates have. Algorithm is suggested that the template of more information should be picked and the others should be discarded. In this way, the proposed method provides HSM with better discriminative ability. Experimental results show that the introduced method achieves good performance in template selection with less computation.
[1] Smale S, Rosasco L, Bouvrie J, et al. Mathematics of the neural response. Foundations of Com- putational Mathematics, 2010, 10(1):67-91.
[2] Bouvrie J, Poggio T, Rosasco L, et al. Generalization and properties of the neural response. 2010.
[3] Li H, Wei Y, Li L, et al. Similarity learning for object recognition based on derived kernel. Neurocomputing, 2012, 83:110-120.
[4] Hartigan J A, Wong M A. Algorithm AS 136: A k-means clustering algorithm. Applied statistics, 1979, pages 100-108.
[5] Li H, Wei Y, Li L, et al. Hierarchical feature extraction with local neural response for image recognition. Cybernetics, IEEE Transactions on, 2013, 43(2):412-424.
[6] Cheng H, Chen Y H, Sun Y. A novel fuzzy entropy approach to image enhancement and thresh- olding. Signal Processing, 1999, 75(3):277-301.
[7] Viola P, Wells III W M. Alignment by maximization of mutual information. International journal of computer vision, 1997, 24(2):137-154.
[8] Pluim J P. Mutual information based registration of medical images. Ponsen & Looijen, 2000, pages p22-p25.
[9] Cover T M, Thomas J A. Elements of information theory. John Wiley & Sons, 2012.
[10] Shannon C E. A mathematical theory of communication. ACM SIGMOBILE Mobile Computing and Communications Review, 2001, 5(1):3-55.
[11] Sabuncu M R. Entropy-based image registration: [PhD Dissertation]. Citeseer, 2004.
[12] Alsaidi R A M, Li H, Wei Y, et al. Hierarchical sparse method with applications In vision and speech recognition. International Journal of Wavelets, Multiresolution and Information Processing, 2013, 11(02).
[13] Alsaidi R A M, Li H, Wei Y, et al. Improved Hierarchical Sparse Method with application to Oine handwritten Arabic character recognition. International Journal of Scienti c, Engineering Research, 2014, 5(03).
[14] Serre T, Wolf L, Bileschi S, et al. Robust object recognition with cortex-like mechanisms. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2007, 29(3):411-426.
[15] Riesenhuber M, Poggio T. Hierarchical models of object recognition in cortex. Nature neuroscience, 1999, 2(11):1019-1025.
RAMADHAN A. M. ALSAIDI, HONG LI, HONGFENG LI, ROKAN KHAJI, "Selection of Informative Template in Hierarchical Sparse Method," International Journal of Mathematics Trends and Technology (IJMTT), vol. 53, no. 6, pp. 488-495, 2018. Crossref, https://doi.org/10.14445/22315373/IJMTT-V53P559
PDF 
Abstract 
Keywords 
References 
Citation