A New Method For Image Classification Based On Multi-Level Neural Networks

• Main Authors: Sadek, Samy, Al-Hamadi, Ayoub, Michaelis, Bernd, Sayed, Usama
• Format: Text
• Language: English
• Published: Zenodo 2009
• Subjects: Image classification; multi-level neural networks; feature extraction; wavelets decomposition.; Chiang; Fang; Lowe; Sea ice
• Online Access: https://dx.doi.org/10.5281/zenodo.1073502; https://zenodo.org/record/1073502

In this paper, we propose a supervised method for color image classification based on a multilevel sigmoidal neural network (MSNN) model. In this method, images are classified into five categories, i.e., "Car", "Building", "Mountain", "Farm" and "Coast". This classification is performed without any segmentation processes. To verify the learning capabilities of the proposed method, we compare our MSNN model with the traditional Sigmoidal Neural Network (SNN) model. Results of comparison have shown that the MSNN model performs better than the traditional SNN model in the context of training run time and classification rate. Both color moments and multi-level wavelets decomposition technique are used to extract features from images. The proposed method has been tested on a variety of real and synthetic images. : {"references": ["Goodrum, \"Image Information Retrieval: An Overview of Current\nResearch\", Special Issue on Information Science Research, vol. 3, no. 2,\n2000.", "N. O- Connor, E. Cooke, H. Le Borgne, M. Blighe, and T. Adamek,\"\nThe aceToolbox: Lowe-Level Audiovisual Feature Extraction for\nRetrieval and Classification\". Proc. of EWIMT-05, Nov. 2005.", "Deng, H. and D.A. Clausi,\"Gaussian MRF Rotation-Invariant Features\nfor SAR Sea Ice Classification,\" IEEE PAMI, 26(7): pp. 951-955, 2004.", "R. Zhao and W. I. Grosky, Bridging the Semantic Gap in Image\nRetrieval, Distributed Multimedia Databases: Techniques and\nApplications, T. K. Shih (Ed.), Idea Group Publishing, Hershey,\nPennsylvania, pp. 14-36, 2001.", "J. Luo, and A. Savakis, \"Indoor vs Outdoor Classification of Consumer\nPhotographs using Low-level and Semantic Features,\" Proc. of ICIP,\npp.745-748, 2001.", "A.K. Vailaya, Jain, and H.-J. Zhang, \"On Image Classification: City\nImages vs. Landscapes,\" Pattern Recognition Journal, vol. 31, pp 1921-\n1936, December, 1998.", "J. Z. Wang, G. Li, and G. Wiederhold, \"SIMPLIcity: Semanticssensitive\nIntegrated Matching for Picture LIbraries,\" In IEEE Trans. on\nPattern Analysis and Machine Intelligence, vol. 23, pages 947-963,\n2001.", "S. Prabhakar, H. Cheng, J.C. Handley, Z. Fan Y.W. Lin, \"Picturegraphics\nColor Image Classification,\" Proc. of ICIP, pp. 785-788, 2002.", "Hartmann and R. Lienhart,\"Automatic Classification of Images on the\nWeb,\" In Proc of SPIE Storage and Retrieval for Media Databases, pp.\n31-40, 2002.\n[10] S. W. Kuffler and J. G. Nicholls, \"From Neuron to Brain,\" (Sinauer\nAssociates, Sunderland, 1976; Mir, Moscow, 1979).\n[11] S. Bhattacharyya and P. Dutta, \"Multiscale Object Extraction with\nMUSIG and MUBET with CONSENT: A Comparative Study,\"\nProceedings of KBCS 2004, pp. 100-109, 2004.\n[12] Yu, H., Li, M., Zhang, H.-J., Feng, J., Color texture moments for\ncontent-based image retrieval, In: Internat. Conf. on Image Processing,\nvol. 3, pp. 929-932, 2002.\n[13] Der-Chiang Li and Yao-Hwei Fang, \"An algorithm to cluster data for\nefficient classification of support vector machines,\" Expert Systems with\nApplications, vol. 34, pp. 2013-2018, 2008.\n[14] R. Marmo et al. \"Textural identification of carbonate rocks by image\nprocessing and neural network: Methodology proposal and examples,\"\nComputers and Geosciences, 31, pp. 649-659, 2005."]}