Applying neural networks to colour image data compression

A self-organizing neural network is used to achieve color image segmentation and image data compression, with an adaptive codebook for faster training. Neural network architectures are well-suited to high speed processing because they are massively parallel. By adding an external threshold decision, a compression network can build its codebook adaptively and therefore speed the compression process. A 24-bit color image is compressed to 6.39 bit with virtually no visual degradation.<
>