Title :
Edge preserving vector quantization using self-organizing map based on adaptive learning
Author :
Kim, K.Y. ; Ra, J.B.
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
Abstract :
The conventional self-organizing map algorithm for vector quantization is modified to reduce the edge degradation in the reproduced image. The learning procedure is performed by a proper selection of the learning rate, which is adaptively determined according to the block activity. The simulation results of 4×4 vector quantization for 512×512 image coding show the feasibility of the proposed method.
Keywords :
adaptive signal processing; edge detection; image coding; image reconstruction; learning (artificial intelligence); self-organising feature maps; vector quantisation; adaptive learning; block activity; edge degradation; edge preserving vector quantization; image coding; neural nets; self-organizing map; Algorithm design and analysis; Artificial neural networks; Clustering algorithms; Degradation; Discrete cosine transforms; Equations; Image coding; Neural networks; Testing; Vector quantization;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.716764