The International Arab Journal of Information Technology (IAJIT)


An Efficient Perceptual of CBIR System using MIL-SVM Classification and SURF Feature Extraction


Hasty increase in use of color image in recent years has motivated to the need of retrieval system for color image. Content Based Image Retrieval (CBIR) system is used to retrieve similar images from large image repositories based on color, texture and shape. In CBIR, the invariance to geometrical transformation is one of the most desired properties. Speeded Up Robust Feature (SURF) and Multiple Instance Learning Support Vector Machine (MIL-SVM) are proposed for extracting invariant features and improving the accuracy of image retrieval respectively. The proposed system consists of the following phases: image segmentation using quad tree segmentation, extraction of features using SURF, classification of images using MIL-SVM, codebook design using Lindae-Buzo-Gray (LBG) algorithm, and measurement of similarity between query image and the database image using Histogram Intersection (HI). In comparison with the existing approach, the proposed approach significantly improves the retrieval accuracy from 74.5% to 86.3%.


[1] Andrews S., Tsochantaridis I., and Hofmann T., “Support Vector Machines for Multiple Instance Learning,” in Proceeding of the 15th International Conference on Neural Information Processing Systems, Cambridge, pp. 577-584, 2002.

[2] Bay H., Tuytelaars T., and Gool L., “Speeded-Up Robust Features (SURF),” Computer Vision and Image Understanding, vol. 110, no. 3, pp. 346- 359, 2008.

[3] Bebis G., Boyle R., Koracin D., and Parvin C., International Symposium on Visual Computing, Springer Berlin Heidelberg, 2005.

[4] Chen H., Ding J., and Sheu H., “Image Retrieval based on Quad Tree Classified Vector Quantization,” Journal of Multimedia Tools and Applications, vol. 72, no. 2, pp. 1961-1984, 2014.

[5] Dujmic H., Rozic N., Begusic D., and Ursic J., “Local Thresholding Classified Vector Quantization with Memory Reduction,” in Proceeding of the First International Workshop on Image Signal Process Anal, Pula, pp. 197- 202, 2000.

[6] Hanmandlu M. and Das A., “Content-based Image Retrieval by Information Theoretic Measure,” Defence Science Journal, vol. 61, no. 5, pp. 415-430, 2011.

[7] Huang J., Kumary S., Mitra M., Zhu W., and Zabih R., “Image Indexing using Color Correlogram,” in Proceeding of Conference on Computer Vision and Pattern Recognition, Washington, pp. 762-768, 1997.

[8] Karnik P. and Shahane N., “A Survey on Content based Image Retrieval using Vector Quantization,” International Journal of Computer Applications, vol. ICRTET, no. 4, pp. 18-22, 2013.

[9] Kelkar D. and Gupta S., “Improved Quad tree Method for Split Merge Image Segmentation,” in Proceeding of First International Conference on Emerging Trends in Engineering and 434 The International Arab Journal of Information Technology, Vol. 14, No. 4, July 2017 Technology, Vancouver, pp. 44-47, 2008.

[10] Kokare M., Biswas P., and Chatterji B., “Texture Image Retrieval using Rotated Wavelet Filters,” Journal of Pattern Recognition Letter, vol. 28, no. 10, pp. 1240-1249, 2007.

[11] Manjunath B., Ohm J., Vasudevan V., and Yamada A., “Color and Texture Descriptors,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 11, no. 6, pp. 703-715, 2001.

[12] Nezamabadi-Pour H. and Saryazdi S., “Object- based Image Indexing and Retrieval in DCT Domain using Clustering Techniques,” World Academy of Science, Engineering and Technology, vol. 3, no. 3, pp. 768-7, 2005.

[13] Paschos G., Radev I., and Prabakar N., “Image Content-based Retrieval using Chromaticity Moments,” IEEE Transactions on Knowledge and Data Engineering, vol. 15, no. 5, pp. 1069- 1072, 2003.

[14] Pass G., Zabih R., and Miller J., “Comparing Images using Color Coherence Vectors,” in Proceeding of the 4th ACM International Conference on Multimedia, Boston, pp. 65-73, 1996.

[15] Quweider M. and Salari E., “Efficient Classification and Codebook Design for CVQ,” IEE Proceedings-Vision, Image and Signal Processing, vol. 143, no. 6, pp. 344-352, 1996.

[16] Salih O., Remaut H., Waksman G., and Orlova E., “Structural Analysis of the Saf Pilus by Electron Microscopy and Image Processing,” Journal of Molecular Biology, vol. 379, no. 1, pp. 174-187, 2008.

[17] Sharma N., Rawat P., and Singh J., “Efficient CBIR using Color Histogram Processing,” International Journal of Signal Image Process, vol. 2, no. 2, pp. 94-112, 2011.

[18] Singh S. and Sontakke T., “An Effective Mechanism to Neutralize the Semantic Gap in Content Based Image Retrieval (CBIR),” The International Arab Journal of Information Technology, vol. 11, no. 2, pp. 124-133, 2014.

[19] Tamijeselvy P., Palanisamy V., and Elakkiya S., “A Novel Watermarking of Images Based on Wavelet Based Contourlet Transform Energized by Biometrics,” WSEAS Transactions on Computers, vol. 12, no. 3, pp. 105-115, 2013.

[20] Tamijeselvy P., Palanisamy V., and Elakkiya S., “Corpus Callosum Classification Using Case Based Reasoning and Genetic Classifier for the Prediction of Epilepsy from 2D Medical Images,” Asian Journal of Information Technology, vol. 12, no. 4, pp. 117-125, 2013.

[21] Tamijeselvy P., Palanisamy V., and Sri-Radhai S., “Segmentation of CSF in MRI Brain Images Using Optimized Clustering Methods,” Asian Journal of Information Technology, vol. 12, no. 4, pp. 109-116, 2013.

[22] Teng S. and Lu G., “Image Indexing and Retrieval based on Vector Quantization,” Pattern Recognition, vol. 40, no. 11, pp. 3299-3316, 2007.

[23] Wang J., Li J., and Wiederhold G., “SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Librarie,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 9, pp. 947-963, 2001.

[24] Xiao Y., Liu B., Cao L., Yin J., and Wu X., “SMILE: A Similarity-Based Approach for Multiple Instance Learning,” IEEE 10th International Conference on Data Mining, Washington, pp. 589-598, 2010.

[25] Yamazaki T., Fujikawa T., and Katto J., “Improving the Performance of SIFT using Bilateral Filter and its Application to Generic Object Recognition,” IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, pp. 945-948, 2012. An Efficient Perceptual of CBIR System using MIL-SVM Classification and SURF Feature Extraction 435 Bhuvana Shanmugam is working as Assistant Professor in the department of Computer Science and Eng., Sri Krishna College of Technology, Coimbatore. Currently she is pursuing her research work in Image Retrieval. Her research interests include Image Processing and Machine Learning. Radhakrishnan Rathinavel is the principal of Vidhya Mandhir Institute of Technology. He received his Ph.D from Anna University Chennai in the year 2008. His research interest includes Wireless Communication, Signal Processing, Networking and Mobile Communication. He has published more than 40 papers in reputed journals and conferences in the field of CDMA systems and Mobile communication Tamije Perumal received her Ph.D in 2013 under Anna University, Chennai. Since 1999, she has been working as faculty in reputed Engineering Colleges. At Present, she is working as Associate Professor in the Department of Computer Science and Engg, Sri Krishna College of Technology, Coimbatore. She has published more than 49 papers in reputed journals and conferences. Her Research interests include Image Processing, Data Mining, and Pattern Recognition. Subhakala Subbaiyan is working as Assistant Professor in Sri Krishna College of Technology. Her Research interests include Data Mining, Image Processing and CBIR.