An improved SOM algorithm and its application to color feature extraction

• Published in: Neural computing & applications Vol. 24; no. 7-8; pp. 1759 - 1770
• Main Authors: Chen, Li-Ping, Liu, Yi-Guang, Huang, Zeng-Xi, Shi, Yong-Tao
• Format: Journal Article
• Language: English
• Published: London Springer London 2014; Springer
• Subjects: Applied sciences; Artificial Intelligence; Coding, codes; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Connectionism. Neural networks; Data Mining and Knowledge Discovery; Data processing. List processing. Character string processing; Exact sciences and technology; Image Processing and Computer Vision; Information, signal and communications theory; Memory organisation. Data processing; Original; Original Article; Pattern recognition. Digital image processing. Computational geometry; Probability and Statistics in Computer Science; Signal and communications theory; Software; Telecommunications and information theory; Competitive mechanism; Self-organizing map; Color feature extraction; Non-principal component; Computer vision; Image processing; Redundancy; Data compression; Competitiveness; Updating; Image compression; Neural network; Winner take all; Kohonen algorithm; Experimental study; Color image; Image analysis; Experimental result; Self organization; Selection criterion; Feature extraction; Pattern extraction; Principal component analysis
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-013-1416-9

Reducing the redundancy of dominant color features in an image and meanwhile preserving the diversity and quality of extracted colors is of importance in many applications such as image analysis and compression. This paper presents an improved self-organization map (SOM) algorithm namely MFD-SOM and its application to color feature extraction from images. Different from the winner-take-all competitive principle held by conventional SOM algorithms, MFD-SOM prevents, to a certain degree, features of non-principal components in the training data from being weakened or lost in the learning process, which is conductive to preserving the diversity of extracted features. Besides, MFD-SOM adopts a new way to update weight vectors of neurons, which helps to reduce the redundancy in features extracted from the principal components. In addition, we apply a linear neighborhood function in the proposed algorithm aiming to improve its performance on color feature extraction. Experimental results of feature extraction on artificial datasets and benchmark image datasets demonstrate the characteristics of the MFD-SOM algorithm.