Parallelized Algorithms for Finding Similar Images and Object Recognition

Rafal Fraczek, Boguslaw Cyganek, Kazimierz Wiatr


The paper addresses the issue of searching for similar images and objects ina repository of information. The contained images are annotated with the helpof the sparse descriptors. In the presented research, different color and edgehistogram descriptors were used. To measure similarities among images, variouscolor descriptors are compared. For this purpose different distance measureswere employed. In order to decrease execution time, several code optimizationand parallelization methods are proposed. Results of these experiments, as wellas discussion of the advantages and limitations of different combinations ofmethods are presented.


color descriptors, code optimization, parallelization, OpenMP

Full Text:



Alhwarin F.: Improved sift-features matching for object recognition. In BCS International Academic Conferenc, pp. 179–190, 2008.

Chee S., Dong K., Soo-Jun P.: Efficient use of mpeg-7 edge histogram descriptor. ETRI Journal, 24(1), 2002.

Cyganek B.: Adding parallelism to the hybrid image processing library in multithreading and multi-core systems. In IEEE 2nd International Conference on Networked Embedded Systems for Enterprise Applications, pp. 1–8, 2011.

Duchenne O., Bach F.: A tensor-based algorithm for high-order graph matching. IEEE Transactions On Pattern Analysis and Machine Intelligence, 33(12), 2011.

Fraczek R., Cyganek B.: Evaluation of image descriptors for retrieval of similar images. Intelligent Tools for Building a Scientific Information Platform Studies in Computational Intelligence, 390:217–226, 2012.

Fraczek R., Grega M., Liebau N., Leszczuk M., Luedtke A., Janowski L., Papir Z.: Ground-truth-less comparison of selected content-based image retrieval measures. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 40:101–108, 2010.

Fukunaga K., Koontz W.: Application of the karhunen-loeve expansion to feature selection and ordering. IEEE Trans. Communications, 19(4), 1970.

Gersho A., Gray R.: Vector Quantization and Signal Compression. Kluwer Academic Publishers, 1992.

Hermes T., Miene A., Herzog O.: Graphical search for images by picture-finder. Multimedia Tools and Applications, Special Issue on Multimedia Retrieval Algorithmics, 2005.

Huang C., Yang X.: Performance analysis and improvement of openmp on software distributed shared memory system. In EWOMP 03, 2003.

Joliffe I. T.: Principal Component Analysis. Springer-Verlag, 1986.

Kandemir M., Choudhary A., et al.: A data layout optimization technique based on hyperplanes. Center for Parallel and Distributed Computing, 1997.

Lowe D. G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Visions, 60(2):91–110, 2004.

Mademlis A., Daras P., Tzovaras D., Strintzis M. G.: 3d volume watermarking using 3d krawtchouk moments. International Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2007.

Manjunath B., Salembier P., Sikora T.: Introduction to MPEG-7: Multimedia Content Description Interface. John Wiley and Sons Ltd., 2002.

Martinez J., Koenen R., Pereira F.: Mpeg-7: the generic multimedia content description standard. IEEE Multimedia, 9(2):78–87, 2002.

Moravec H. P.: Towards automatic visual obstacle avoidance. In Proc. of the 5th International Joint Conference on Artificial Intelligence, p. 584, 1977.

Murase H., Nayar S.: Detection of 3d objects in cluttered scenes using hierarchical eigenspace. Pattern Recognition Letters, 18(4), 1997.

Poliwoda M.: Automatically loops parallelized, efficiency of parallelized code. PAK, 54(8), 2008.

similar images finder.: online.

Yan K., Sukthankar R.: Pca-sift: A more distinctive representation for local image descriptors. In Proc. of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 506–513, 2004.

Yang N. C., Kuo C. M., Chang W. H., Lee T. H.: A fast method for dominant color descriptor with new similarity measurer. Journal of Visual Communication and Image Representation, 19(2):92–105, 2008.



  • There are currently no refbacks.