Image retrieval systems are used to search and browse the images from large digital image databases and retrieval of these images. Content-Based Image Retrieval (CBIR) gives an efficient approach to browse and retrieve images from these large databases, but the semantic gap between low-level and high-level features is a big issue. To overcome this issue Particle Swarm Optimization is used with a new combination of low-level features. Moments can be used to characterize the color distribution of an image. A color feature of an image is extracted by calculating color moments which are unique and invariant to rotation and scaling. Rotated Local Binary Pattern is used to extract texture information from the image, it is invariant to rotation and scaling. Edges give the object representation of an image and used as a feature descriptor for image retrieval, Here Edge Histogram Descriptor is used to find out the abruptly changes in the pixel value of the image. Edge Histogram Descriptor (EHD) provides the spatial information about five types of edges of an image. For performance evaluation, we simply used weighted Euclidian distance with optimal weights and calculate Average precision, recall and accuracy. Experiment result shows that the proposed method gives improved precision and recall in comparison to existing method. The efficiency of proposed system is tested for three types of datasets: WANG dataset, LI dataset and Caltech-101 image dataset.

CBIR, feature extraction, color Moments, RLBP, EHD, PSO

[1] J. Kennedy and R. Eberhart. Particle swarm optimization. In Proceedings of IEEE International Conference on Neural Networks, volume IV, pages 1942{1948, Perth, Australia, 1995.
[2] Y. Shi and R.C. Eberhart. A modified particle swarm optimizer, In Proceedings of 1998 IEEE International Conference on Evolutionary Computation, pages 69{73, Anchorage, AK, USA, 1998.
[3] Zeyad Safaa Younus et al., “Content-based image retrieval using PSO and k-means clustering algorithm,” springer, Saudi Society for Geosciences 2014.
[4] Chatzichristofis, S., Boutalis, Y.: A Hybrid Scheme for Fast and Accurate Image Retrieval Based on Color Descriptors. In: De Mallorca, P. (ed.) IASTED International Conference on Artificial Intelligence and Soft Computing (ASC 2007), Spain 2007.
[5] Rakesh Mehta, Karen Egiazarian, "Dominant Rotated Local Binary Patterns (DRLBP) for Texture Classification", Pattern Recognition Letters, © Elsevier 2015.
[6] R. Gali, M. Dewal, and R. Anand, "Genetic Algorithm for Content-Based Image Retrieval," Fourth International Conference on Computational Intelligence, Communication Systems and Networks, 2012.
[7] Savvas A. Chatzichristofis and Yiannis S. Boutalis, “CEDD: Color and Edge Directivity Descriptor. A Compact Descriptor for Image Indexing and Retrieval,” © Springer-Verlag Berlin Heidelberg pp. 312–322, 2008.
[8] S. Sankar Ganesh and K. Ramar, "Content-Based Image Retrieval using heuristic Particle Swarm Optimization," Asian Journal of Information Technology ISSN: (1682-3915), 2016.
[9] Ekta Gupta, and Rajendra Singh Kushwah, “Combination of Global and Local Features using DWT with SVM for CBIR”, IEEE 978-1-4673-7231-2/15/$31.00, @ 2015.
[10] Saeed Sadri et al. , An Efficient content-based image retrieval with ant colony optimization feature selection scheme based on wavelet and color features" International Symposium on Artificial Intellegence and Signal Processing, 2015.
[11] Ojala, T., Pietikainen, M., and Maenpaa, T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE TPAMI, 24(7):971 –987, 2000.
[12] G. Saranya, K. Anitha, A. Chilambuchelvan, “AN EFFICIENT APPROACH TO AN IMAGE RETRIEVAL USING PARTICLE SWARM OPTIMIZATION”, International Journal of Computer Science and Mobile Computing, Vol.3 Issue.4, pg. 1053-106, April- 2014.
[13] Raj Singh, Dr. Shruti Kohli, "Enhanced CBIR using Color Moments, HSV Histogram, Color Auto Correlogram, and Gabor Texture", International Journal of Computer Systems (ISSN: 2394-1065), Volume 02– Issue 05, May 2015.
[14] Sawat Somnugpong, and Kanokwan Khiewwan, ”Content- Based Image Retrieval Using a Combination of Color Correlograms and Edge Direction Histogram,” 978-1-5050-2033-1/16/©2016 IEEE.
[15] R. Choudhary, N. Raina, N. Chaudhary and R Chauhan, "An integrated Approach to Content-Based Image Retrieval", IEEE, pp. 2404-2410, Sept. 2014.
[16] Amit Singla, Meenakshi Garg,” CBIR Approach Based On Combined HSV, Auto Correlogram, Color Moments and Gabor Wavelet", International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3, Issue 10 October 2014.
[17] A. Ananth, Dr. K. Mala and S. Sauganya, "Content-Based Image Retrieval System based on Semantic Information using Color, Texture and Shape Features", IEEE 978-1-4673-8437-7/16/$31.00 © 2016.
[18] Mohd. Aquib Ansari, and Manish Dixit, “An Image Retrieval Framework: A Review”, International Journal of Advanced Research in Computer Science, ISSN No. 0976-5697, Volume 8, No. 4, May – June 2017.
[19] Diksha Kurchaniya, and Punit Kumar Johari, "Analysis of Different Similarity Measures in Image Retrieval Based on Texture and Shape”, International Research Journal of Engineering and Technology (IRJET), Volume: 04 Issue: 04, e-ISSN: 2395-0056, p-ISSN: 2395-0072, Apr -2017.