Fast and Accurate Home Photo Categorization for Handheld Devices using MPEG-7 Descriptors
Keywords:machine learning, feature extraction, image classification, mobile computing, content based retrieval
Home photo categorization has become an issue for practical use of photos taken withÂ various devices. But it is a difficult task because of the semantic gap between physicalÂ images and human perception. Moreover, the object-based learning for overcomingÂ this gap is hard to apply to handheld devices due to its computational overhead. WeÂ present an efficient image feature extraction method based on MPEG-7 descriptorsÂ and a learning structure constructed with multiple layers of Support Vector MachinesÂ for fast and accurate categorization of home photos. Experiments on diverse homeÂ photos demonstrate outstanding performance of our approach in terms of the categorizationÂ accuracy and the computational overhead.
J.H. Lim, J.S.Jin, Unifying local and global content-based similarities for home photo re- trieval, Proceedings of 2004 International Conference on Image Processing, 4:2371-2374, 2004.
Y. Chen and J.Z. Yang, Image Categorization by Learning and Reasoning with Regions, The Journal of Machine Learning Research, 5:913-939, 2004.
S.J. Yang, S.K. Kim, K.S. Seo, Y.M. Ro, J.Y. Kim, Y.S. Seo, Semantic categorization of digital home photo using photographic region templates, Proceedings of 2005 Information retrieval research in Asia, 43(2):503-514, 2007.
J.M. Mart ÌÄ±nez, MPEG-7 Overview, ISO/IEC JTC1/SC29/WG11N6828, 2004.
C.J.C. Burges, A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, 2(2):121-167, 1998. http://dx.doi.org/10.1023/A:1009715923555
T. Mitchell, Machine Learning, McGraw Hill, 1998.
H. Eidenberger, Statistical analysis of content-based MPEG-7 descriptors for image retrieval, Multimedia Systems, 10:84-97, 2004. http://dx.doi.org/10.1007/s00530-004-0141-8
J.S. Yu, J.H. Nang, An Optimization Method for Extraction of MPEG-7 Color Structure Descriptor and Dominant Color Descriptor, Proceedings of Korea Computer Congress 2009, 36(1A):320-321, 2009.
Institute for Integrated Circuits, Technische Universitt Munchen, MPEG-7 XM Software, Germany, 2003. Available (Online): http://standards.iso.org/ittf/PubliclyAvailableStandards/c035364ISOIEC15938-6%28E%29ReferenceSoftware.zip
B. Fr Ìˆoba, A. Ernst, Face Detection with the Modified Census Transform, Sixth IEEE In- ternational Conference on Automatic Face and Gesture Recognition, 0:91-96, 2004.
B.H. Oh, J.H. Yang, Discovering Classification Rules using Genetic Algorithm, Proceedings of Korea Computer Congress 2009, 36(1C):480-485, 2009.
T.F. Wu, C.J. Lin, R.C. Weng, Probability Estimates for Multi-class Classification by Pairwise Coupling, Journal of Machine Learning Research, 5:975-1005, 2003.
C.C. Chang, C.J. Lin, LIBSVM : a library for support vector machines, 2001.
M.M. Jlasi, A. Douik, H. Messaoud, Objects Detection by Singular Value Decomposition Technique in Hybrid Color Space: Application to Football Images, International Journal of Computers Communications & Control, 5(2):193-204, 2010.
T. Barbu, An Automatic Face Detection System for RGB Images, International Journal of Computers Communications & Control, 6(1):21-32, 2011.
ONLINE OPEN ACCES: Acces to full text of each article and each issue are allowed for free in respect of Attribution-NonCommercial 4.0 International (CC BY-NC 4.0.
You are free to:
-Share: copy and redistribute the material in any medium or format;
-Adapt: remix, transform, and build upon the material.
The licensor cannot revoke these freedoms as long as you follow the license terms.
DISCLAIMER: The author(s) of each article appearing in International Journal of Computers Communications & Control is/are solely responsible for the content thereof; the publication of an article shall not constitute or be deemed to constitute any representation by the Editors or Agora University Press that the data presented therein are original, correct or sufficient to support the conclusions reached or that the experiment design or methodology is adequate.