Abstract   Digital image retrieval is one of the major concept s in image processing. In this paper, a novel appro ach is proposed to retrieve digital images from huge datab ases which using texture analysis techniques to extract discriminant features together with color and shape features. Th e proposed approach consist three steps. In the first one, shape detection is done based on top(hat transform to detect and crop main object parts of the image, especially complex ones. Second step is included a texture feature representation algorithm which used Color Local Binary Patterns (CLBP) and local variance as discriminant operators. Finally, to retrieve mostly closing matching images to the query, log likeliho od ratio is used. In order to, decrease the computational complexity, a novel algorithm is prepared disregarding not similar cate gories to the query image. It is done using log(likelihood ratio as non (similarity measure and threshold tuning technique. The performance of the proposed approach is evaluated applying on corel an d simplicity image sets and it compared by some of other well(known approaches in terms of precision and recall which s hows the superiority of the proposed approach. Low noise sensitivity, rotation invariant, shift invariant, gray scale inv ariant and low computational complexity are some of other advantages.  

References

[1] Banerjeea M., Malay K., and Maji P., Content- based Image Retrieval using Visually Significant Point Features, Fuzzy Sets and Systems , vol. 160, no. 23, pp. 3323-3341, 2009.

[2] Belongie S., Malik J., and Puzicha J., Shape Matching and Object Recognition using Shape Contexts, IEEE Transactions on Pattern 580 The International Arab Journal of Information Tech nology, Vol. 12, No. 6, November 2015 Analysis and Machine Intelligence , vol. 24, no. 4, pp. 509-522, 2002.

[3] Berman P. and Shapiro G., A Flexible Image Database System for Content-Based Retrieval, Computer Vision and Image Understanding , vol. 75, no. 1, pp. 175-195, 1998.

[4] Chen T., Wu H., Rahmani R., and Hughes J., A Pseudo Top-Hat Mathematical Morphological Approach to Edge Detection in Dark Regions, Pattern Recognition , vol. 35, no. 1, pp. 199-210, 2002.

[5] Eidenberger H., Statistical Analysis of MPEG-7 Image Descriptions, Multimedia Systems, vol. 10, no. 2, pp. 84-97, 2004.

[6] Fekri-Ershad S. and Tajeripour F., A Robust Approach for Surface Defect Detection based on One Dimensional Local Binary Patterns, Indian Journal of Science and Technology , vol. 5, no. 8, pp. 3197-3203, 2012.

[7] Guang L., Lei Z., Ying H., Zuo-Yong Li., and Jing-Yu Y., Image Retrieval Based on Multi- Texton Histogram, Pattern Recognition, vol. 43, no. 7, pp. 2380-2389, 2010.

[8] Guang L., Zuo L., Lei Z., and Yong X., Image Retrieval based on Micro-Structure Descriptor, Pattern Recognition , vol. 44, no. 9, pp. 2123- 2133, 2011.

[9] Jhanwar N., Chaudhuri S., and Zavidovique B., Content based Image Retrieval using Motif Co- Occurrence Matrix, Image and Vision Computing , vol. 22, no. 14, pp. 1211-1220, 2004.

[10] Kekre B., Mukherje P., and Wadwa S., Image Retrieval with Shape Features Extracted using Morphological Operators with BTC, the International Journal of Computer Applications , vol. 12, no. 3, pp. 1-5, 2010.

[11] Malik F. and Baharudin B., Effective Image Retrieval Based on Experimental Combination of Texture Features and Comparison of Different Histogram Quantization in the DCT Domain, the International Arab Journal of Information Technology , vol. 11, no. 3, pp. 258-267, 2014.

[12] Manjunath S. and Ma Y., Texture Features for Browsing and Retrieval of Image Data, IEEE Transaction on Pattern Analysis and Machine Intelligence , vol. 18, no. 8, pp. 837-842, 1996.

[13] Ojala T., Pietikainen M., and Maenpaa T., Multi Resolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns, IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 24, no. 7, pp. 971- 987, 2002.

[14] Ojala T., Rautiainen M., Matinmiko E., and Aittola M., Semantic Image Retrieval with HSV Correlograms, available at: http://www.mediateam.oulu.fi/publications/pdf/6 8.p, last visited 2013.

[15] Pass G. and Zabih R., Comparing Images using Joint Histograms, Journal of Multimedia Systems , vol. 7, no. 3, pp. 234-240, 1999.

[16] Pietik inen M., Ojala T., and Xu Z., Rotation- Invariant Texture Classification using Feature Distributions, Pattern Recognition , vol. 33, no. 1, pp 43-52, 2000.

[17] Randen T. and Husoy H., Filtering for Texture Classification: A Comparative Study, IEEE Transaction Pattern Analysis and Machine Intelligence , vol. 21, no. 4, pp. 291-310, 1999.

[18] Tajeripour F. and Fekri-Ershad S., Developing a Novel Approach for Stone Porosity Computing using Modified Local Binary Patterns and Single Scale Retinex, the Arabian Journal for Science and Engineering , vol. 39, no. 2, pp. 875-889, 2014.

[19] Stanford Vision Lab., available at: http://vision.stanford.edu/, last visited 2014. Farshad Tajeripour received his BSc and MSc degrees in electrical engineering from Shiraz University, in 1994 and 1997, respectively and the PhD degree in electrical engineering from the Tarbiat Modarres University of Tehran, in 2007. In 2007, he joined the Department of Electric al and Computer Engineering at Shiraz University, Shiraz, as an Assistant Professor. His research int erests include digital image processing, machine vision, medical image processing, signal processing, and th e design and implementation of vision based inspectio n systems. He has published several papers in the fie lds of pattern recognition, signal and image processing . Mohammad Saberi received his BSc degree in computer software engineering from Islamic Azad University of Najaf-Abad, Iran in 2008 and his MSc degree from Shiraz University, Iran in 2013, majored in artificial intelligence. He joined the Isfahan Municipality Information and Communication Organization in 2013. His research interests are skin detection, texture analysis and image retrieval and etc. Developing a Novel Approach for Content Based Image Retrieval Using 581 Shervan Fekri-Ershad received his BSc degree in computer hardware engineering from Islamic Azad University of Najaf-Abad, Iran in 2009 and his MSc degree from Shiraz University, Iran in 2012, majored in artificial intelligence. Currently, he is a PhD student in the School of electrical and computer engineering, Shiraz Univers ity, Iran. He joined the department of Computer Engineering at Amin University, Isfahan, as a lectu rer in 2012. His research interests are image processin g applications includes visual inspection systems, vi sual classification, texture analysis, surface defect de tection and etc.