Block matching algorithm using neural network
Dae-Hyun Ryu · 2002
This paper presents a new search region prediction method using the neural network vector quantization (VQ) for motion estimation. A major advantage of formulating VQ as a neural network is that the large number of adaptive training algorithms that are used for neural networks can be applied to VQ. The proposed method reduces the computation because of the smaller number of search points than conventional methods, and reduces the bits required to represent motion vectors. The results of computer simulation show that the proposed method provides better PSNR than other block matching algorithms.