Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers (1994)
Pacific Grove, CA, USA
Oct. 31, 1994 to Nov. 2, 1994
K.S. Thyagarajan , Dept. of Electr. & Comput. Eng., San Diego State Univ., CA, USA
D. Erickson , Dept. of Electr. & Comput. Eng., San Diego State Univ., CA, USA
This paper describes a design of Kohonen's self-organizing neural networks as learning vector quantizers (LVQ) to compress video images. Both fixed rate and variable rate LVQs have been designed. For fixed rate LVQs, both full search and tree-structured codebooks are designed. Further, this paper describes the design of variable rate LVQs. Variable rate LVQs, structured as unbalanced trees, are found to provide improved performance of up to 3 dB peak SNR over comparable fixed rate LVQs.<
video coding, vector quantisation, self-organising feature maps
K. Thyagarajan and D. Erickson, "Variable rate self organizing neural networks for video compression," Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers(ACSSC), Pacific Grove, CA, USA, 1995, pp. 244-248.