The Counterpropagation Network (CPN) can be applied to image compression as a vector quantizer. However, the CPN learning algorithm has two obvious disadvantages in codebook designing.
对向传播神经网络(CPN)可以作为矢量量化器用于图像压缩，但CPN学习算法在进行码书设计时存在两个明显的缺陷。
Computer simulations show that the training speed of codebook is quickened by the new design algorithm and the complexity of vector quantizer is reduced.
计算机模拟结果表明，新算法明显缩减了码本训练时间、提高了矢量量化的速度。
应用推荐