Title :
Adaptive learning method in self-organizing map for edge preserving vector quantization
Author :
Kim, Y.K. ; Ra, J.B.
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea
fDate :
1/1/1995 12:00:00 AM
Abstract :
The Kohonen´s self-organizing map algorithm for vector quantization of images is modified to reduce the edge degradation in the coded image. The learning procedure is performed by adaptive learning rates that are determined according to the image block activity. The simulation result of 4×4 vector quantization for 512×512 image coding demonstrates the feasibility of the proposed method
Keywords :
image coding; learning (artificial intelligence); self-organising feature maps; vector quantisation; 262144 pixel; 512 pixel; Kohonen´s self-organizing map; adaptive learning; coded image; edge degradation; edge preserving vector quantization; image block activity; Algorithm design and analysis; Clustering algorithms; Degradation; Discrete cosine transforms; Image coding; Iterative algorithms; Iterative methods; Learning systems; Neural networks; Vector quantization;
Journal_Title :
Neural Networks, IEEE Transactions on
