基于矢量量化与神经网络的调色板设计

VECTOR QUANTIZATION AND NEURAL NETWORKS FOR PALETTE ACCORDING TO IMAGE

用基于神经网络的关量量化方法实现面向图象的调色板设计，以均匀颜色空间的距离作失真测度，以矢量量化的码书设置颜色寄存器的颜色值。实验证明，效果令人满意。

Palette According to Image (PAI) is implemented using a neural network based on vector quantization technique. The distance of the uniform color space is used as the distortion measure, and the codebook of vector quantization is used to set the color table register, which shows good results.