Efficient System for Color Logo Recognition Based on Self-Organizing Map and Relevance Feedback Technique
This paper proposes an efficient system for color logo recognition. The proposed logo retrieval approach uses self-organizing map (SOM) and relevance feedback based on three types of query improvement policies: new query point, query rewriting, and query development. Feature extraction techniques are implemented for representing the visual features of the images from the data set as well as the query image. For color feature extraction, color histogram, color moments, and color correlogram techniques are used. For texture feature extraction, Gabor wavelet and Haar wavelet are implemented. And for shape feature extraction, Fourier descriptor and circularity features are used. The topological mapping property of the SOM is used to map these database features. This map contains the comparable images arranged closer to each other. The data set consists of about 3000 color logo images. Euclidian distance is used for similarity computation. The proposed approach is able to recognize the logo images with good retrieval efficiency. The results obtained are remarkable after the integration of SOM with relevance feedback technique.
KeywordsContent-based image retrieval (CBIR) Feature vector Logo Relevance feedback Self-organizing map (SOM)
- 3.Pinjarkar, L., Sharma, M., Mehta, K.: Comparative evaluation of image retrieval algorithms using relevance feedback and it’s applications. Int. J. Comput. Appl. (IJCA) 48(18), 12–16 (2012)Google Scholar
- 8.Vesanto, J., Himberg, J., Alhoniemi, E., Parhankangas, J.: Self-organizing map in MATLAB: the SOM Toolbox. In: Proceedings of the MATLAB DSP Conference Nov 16–17, Espoo, Finland, pp. 35–40 (1999)Google Scholar
- 10.Alnihaud, J.: Content based image retrieval system based on self organizing map, fuzzy color histogram and subtractive fuzzy clustering. Int. Arab J. Inf. Technol. 9(5), 452–458 (2012)Google Scholar
- 12.Long, F., Zhang, H., Feng, D.D.: Multimedia information retrieval and management. In: Chapter-1 Fundamentals of Content-Based Image Retrieval, pp. 1–26. Springer, Berlin (2003) Google Scholar