Fast and accurate algorithms are necessary for Content based image retrieval (CBIR) systems to perform operations on compressed images databases such as jpeg or through compressive sensing. Feature extraction and feature matching are two important steps in any CBIR system. Wrong matching may affect the accuracy rate of CBIR systems. The matching of query image which is in uncompressed form to image in database which is in compressed form is very challenging. However, existing algorithms suffer from a flawed tradeoff between accuracy and speed. In this research work, shape based image retrieval is carried out using modified standard DCT approach and parallelized it on Graphics Processing Unit (GPU). The main goal of this research work is to make CBIR faster for processing a large number of images database using parallel implementation of algorithms on GPU. GPUs are emerging as powerful parallel systems at a cheaper cost. Our work employs extensive usage of highly multithreaded architecture and shared memory of multi-cored GPU. An efficient use of shared memory is required to optimize parallel reduction in Compute Unified Device Architecture (CUDA). Experimental results show that our method can achieve a speedup of about 15x over the serial implementation when running on a GPU named GeForce 9500 GT having 32 cores. Shape based retrieval method of CBIR is also evaluated using Recall, Precision, F-measure, True Negative rate, and Accuracy evaluation measures.

1. Antonio da Luz Jr, Daniel D. Abdala, Aldo v.wangenheim, Eros Comunello,“ Improving Performance and Quality in Content-Based Medical Image Retrieval”, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07) .
2. Mohamad Obeid’, Bruno Jedynak, Mohamed Daoudi, “Improving Performance and Quality in Content-Based Medical Image Retrieval”, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07) .
3. Aliaa.A.A.Yousiff, A.A. Darwish, R.A. Mohmed,“ Content based medical image retrieval based on pyramid structure wavelet”, IJCSNS International Journal of Computer Science and Network Security, VOL.10 No.3, March 2010
4. T. M. Lehmann, M. O. Güld, C. Thies, B. Fischer, K. Spitzer, D. Keysers, H. Ney,M. Kohnen, H. Schubert, B. B. Wein, “Content-based Image Retrieval in Medical Applications”, 2004.
5. Yong Rui and Thomas S. Huang, Shih-Fu Chang, “Image Retrieval: Current Techniques, Promising Directions, and Open Issues”, Journal of Visual Communication and Image Representation 10, pp 39–62 1999 .http://www.idealibrary.com on ideal.
6. Ch. Theoharatos, V.K. Pothos, G. Economou and S. Fotopoulos, “compressed domain image indexing and retrieval based on the minimal spanning tree”, 2005.
7. Matthew J. Zukoski, Terrance Boult, “ A novel approach to medical image compression”, Int. J. Bioinformatics Research and Applications, Vol. 2, No. 1, 2006
8. Daidi. Zhong, Irek. Defeel, “Study of Image Retrieval Based on Feature Vectors in Compressed Domain”.
9. Jinshan Tang, Eli Peli, and Scott Acton, “Image Enhancement Using a Contrast Measure in the Compressed Domain”, IEEE signal processing letters, vol. 10, no. 10, october 2003
10. Salih Burak Gokturk, Carlo Tomasi, Bernd Girod, Chris Beaulieu, “ medical image compression based on region of interest, with application to colon ct images”, Electrical Engineering, Computer Science, Radiology Departments, Stanford University
11. Vidya R. Khapli, Anjali S Bhalchandra, “Compressed Domain Image Retrieval Using Thumbnails of Images”, First International Conference on Computational Intelligence, Communication Systems and Networks, 978-0-7695-3743-6/09 2009.
12. Ruey-Feng Chang, Wen-Jia Kuo and Hung-Chi Tsai, “image retrieval on uncompressed and compressed domains”, Department of Computer Science and Information Engineering , National Chung Cheng University, Chiayi, Taiwan 621, R.O.C., 0-7803-6297-7/00/ 2000 .
13. Rami Al-Tayeche and Ahmed Khalil, “CBIR: Content Based Image Retrieval”Department of Systems and Computer Engineering Faculty of Engineering Carleton University” Tech. Rep. April 4, 2003.
14. M. Hatzigiorgaki and A. N. Skodras, “Compressed Domain Image Retrieval: A Comparative Study of Similarity Metrics”, Visual Communications and Image Processing Touradj Ebrahimi, Thomas Sikora, Editors, Proceedings of SPIE Vol. 5150 (2003)
15. Gerald Schaefer and Roman Starosolski, “A comparison of two methods for retrieval of medical images in the compressed domain”, 30th Annual International IEEE EMBS Conference Vancouver, British Columbia, Canada, August 20-24, 2008.
16. Farzad Zargari, Ali Mosleh and Mohammad Ghanbari, “ A Fast and Efficient Compressed Domain JPEG2000 Image Retrieval Method”, IEEE Transactions on Consumer Electronics, Vol. 54, No. 4, november 2008
17. Lin NI, “A Novel Image Retrieval Scheme in JPEG2000 Compressed Domain Based on Tree Distance”,ICICS-PCM 15 Dec ,2003.
18. A.Ashbrook and N.A.Thacker, “Tutorial: Algorithms for 2-Dimensional Object Recognition”, 1 / 12 / 1998.
19. Fernando, R and Kilgard, M. J. The Cg tutorial the definitive guide to programmable real-time graphics. Addison-Wesley 2003.
20. Moravanszky, Linear algebra on the GPU, in: W.F. Engel (Ed.), Shader X 2, Wordware Publishing, Texas,2003.
21. Manocha, D. “Interactive geometric & scientific computations using graphics hardware”, SIGGRAPH 2003
22. Moreland, K. and Angel E. The FFT on a GPU. In Proceedings of SIGGRAPH Conference on Graphics Hardware, 112-119, 2003.
23. Mairal, J., Keriven, R. and Chariot, A. “Fast and efficient dense variational Stereo on GPU”. In Proceedings of International Symposium on 3D Data Processing, Visualization, and Transmission, 97-704, 2006.
24. Yang, R. and Welch, G. “Fast image CBIR and smoothing using commodity graphics hardware”. Journal of Graphics Tools, Vol. 17, (4), 91-100, 2002.
25. Fung, J. and Man, S. OpenVIDIA: Parallel GPU computer vision. In Proceedings of ACM International Conference on Multimedia, pp. 849-852, 2005.
26. Owens, J. D. Luebke, D., Govindaraju, N., Harris, M., Kruger, J., Lefohn, A. E. and Purcell, T. J. “A survey of general-purpose computation on graphics hardware”. In proceeding of Eurographics, State of the Art Reports, 21–51, 2005.
27. Larsen, E. S., McAllister, D. “Fast Matrix Multiplies using Graphics Hardware”. In Proceeding of International Conference for High Performance Computing and Communications, pp.159-168, 2001.
28. Trendall C. and Stewart, A. J. “General calculations using graphics hardware with applications to interactive caustics. Rendering Techniques”: 11th Eurographics Workshop on Rendering, 287-298, 2000.
29. Li, Wei, Wei, Xiaoming, A. and Kaufman, “Implementing lattice boltzmann computation on graphics hardware”. In proceeding of the International Conference for High Performance Computing and Communications.
30. M. Emmanuel, D.R. Ramesh Babu, Jayashree Jagdale, Pravin Game and G.P. Potdar,” Parallel Approach for Content Based Medical Image Retrieval System”, Journal of Computer Science 6 (11):pp. 1258-1262, 2010.
31. NVIDIA CUDA Programming Guide Version 2.0, available at www.nvidia.com/object/cuda_develop.html.
32. NVIDIA Corporation: NVIDIA CUDA programming guide. Jan 2007, available at http://developer.download.nvidia.com/compute/cuda/2_0/docs/NVIDIA_CUDA_Programming_Guide_2.0.pdf
33. Zhang Xihuang, Bian Guochun,Xu Wenbo, “A Shape Feature Based Image Retrieval in DCT Compressed-Domain”,The Fifth International Conference on Computer and Information Technology (CIT’05), Proceedings of the 2005.

Shape based Image Retrieval Parallelization GPU CUDA