The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


Model Based Approach for Content Based Image

1,
#
  This  paper  proposes  a  methodology  for  Content  Based   Image  Retrievals  (CBIR)  using  the  concept  of  fusion  and  relevancy  mechanism  based  on  KL  divergence  associat ed  with  generalized  gamma  distribution  to  integrate  the  features  corresponding to multiple modalities, feature level  fusion technique is considered. The relevancy appr oach considered bridges  the  link  to  both  high  level  and  low  level  features.   The  target  in  the  CBIR  is  to  retrieve  the  images  o f  relevancy  based  on  the  query and retrieving the most relevant images optim izing the time complexity. A generalized gamma distribution is considered  in  this  paper  to  model  the  parameters  of  the  query  image  and  basing  on  the  maximum  likelihood  estimati on  the  generalized  gamma  distribution,  the  most  relevant  images  are  re trieved.  The  parameters  of  the  generalized  gamma  di stribution  are  updated  using  the  EM  algorithm.  The  developed  model   is  tested  on  the  brain  images  considered  from  brain  web  data  of  UCI  database. The performance of the model is evaluated  using precision and recall. 


[1] Burghouts G. and Geusebroek J., Performance Evaluation of Local Colour Invariants, Computer Vision and Image Understanding , vol. 113, no. 1, pp. 48C62, 2009.

[2] Chahooki M. and Charkari N., Shape Retrieval Based on Manifold Learning by Fusion of Dissimilarity Measures, Image Processing, IET , vol. 6, no. 4, pp. 327C336, 2012.

[3] Datta R., Li J., and Wang J., ContentCBased Image Retrieval: Approaches and Trends of the New Age, in Proceedings of the 7 th ACM SIGMM International Workshop on Multimedia Information Retrieval , New York, USA, pp. 253C 262, 2005.

[4] De Ves E., Benavent X., Ruedin A., Acevedo D., and Seijas L., WaveletCBased Texture Retrieval Modeling the Magnitudes of Wavelet Detail Coefficients with a Generalized Gamma Distribution, in Proceedings of the 20 th International Conference on Pattern Recognition , Istanbul, Turkey, pp. 221C224, 2010.

[5] Goldberger J., Gordon S., and Greenspan H., An Efficient Image Similarity Measure Based on Approximations of KLCDivergence Between Two Gaussian Mixtures, in Proceedings of the International Conference on Computer Vision , Nice, France, pp. 487C493, 2003.

[6] Grigorova A., De Natale F., Dagli C., and Huang T., ContentCBased Image Retrieval by Feature Adaptation and Relevance Feedback, IEEE Transactions on Multimedia , vol. 9, no. 6, pp. 1183C1192, 2007.

[7] Hsu C. and Li C., Relevance Feedback using Generalized Bayesian Framework with RegionC Based Optimization Learning, IEEE Transactions on Image Processing , vol. 14, no. 10, pp. 1617C1631, 2005.

[8] Kher M., Ziou D., and Bernardi A., Combining Positive and Negative Examples in Relevance Feedback for ContentCBased Image Retrieval, the Journal of Visual Communication and Image Representation , vol. 14, no. 4, pp. 428C457, 2003.

[9] Malik F. and Baharudin B., The Statistical Quantized Histogram Texture Features Analysis for Image Retrieval based on Median and Laplacian Filters in the DCT Domain, the International Arab Journal of Information Technology , vol. 10, no. 6, pp. 616C624, 2013.

[10] Marakakis A., Siolas G., Galatsanos N., Likas A., and Stafylopatis A., Relevance Feedback Approach for Image Retrieval Combining Support Vector Machines and Adapted Gaussian Mixture Models, Image Processing, IET , vol. 5, no. 6, pp. 531C540, 2011.

[11] Qian F., Li M., Zhang L., Zhang H., and Zhang B., Gaussian Mixture Model for Relevance Feedback in Image Retrieval, in Proceedings of IEEE International Conference on Multimedia and Expo , Lausanne, Switzerland, pp. 229C232, 2002.

[12] Rui Y., Huang T., and Chang S., Image Retrieval: Current Techniques, Promising Direction and Open Issues, the Journal of Visual Communication and Image Representation , vol. 10, no. 1, pp. 39C62, 1999.

[13] Sivakamasundari G. and Seenivasagam V., Different Relevance Feedback Techniques in CBIR: A Survey and Comparative Study, in Proceedings of International Conference on Computing , Electronics and Electrical Technologies , Tamil, India, pp. 1115C1121, 2012.

[14] Smeulders A., Worring M., Santini S., Gupta A., and Jain R., ContentCBased Image Retrieval at the End of the Early Years, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 12, pp. 1349C1380, 2000. Model Based Approach for Content Based Image Retrievals Based on Fusion 523

[15] Su Z., Zhang H., Li S., and Ma S., Relevance Feedback in ContentCBased Image Retrieval: Bayesian Framework, Feature Subspaces and Progressive Learning, IEEE Transactions on Image Processing , vol. 12, no. 8, pp. 924C937, 2003.

[16] Vasconcelos N., Minimum Probability of Error Image Retrieval, IEEE Transactions on Signal Processing , vol. 52, no. 8, pp. 2322C2336, 2004. Telu Venkata Madhusudhanarao received his BTech degree from JNT University, Kakinada, India, and MTech degree from JNT University Anantapur, India. Currently, he is working as an Associate Professor in the Department of Computer Science and Engineering at Thandra Paparaya Institu te of Science and Technology (TPIST), Bobbili. He is pursuing his PhD in the Department of Computer Science and Engineering, at JNT University, Kakinad a, India. His research interests include image process ing, knowledge discovery and data mining, computer visio n and image analysis. Sanaboina Pallam Setty received his PhD degree in computer science and systems engineering from Andhra University, Visakhapatnam, India. Currently, he is working as a Professor in the Department of Computer Science and Systems Engineering at Andhra University, Visakhapatnam, India. He has 21 years of teaching and research experience. He has guided 4 students for PhD and guiding 12 scholars for PhD. His current research interests are in the areas of image processing, com puter vision and image analysis, computer networks, and modeling and simulation. Yarramalle Srinivas received his PhD degree in computer science with Specialization in Image Processing from Acharya Nagarjuna University, Guntur, India. Currently, he is working as a Professor in the Department of Information Technology at GITAM University, Visakhapatnam, India. He has 17 years of teaching and research experience. He has guided two students for PhD and guiding eight scholars for PhD. His current researc h interests are in the areas of image processing, knowledge discovery and data mining, computer visio n and image analysis.