Neural network adaptive image coding
Hendrik J. Niemann, Junhui Wu · IEEE Transactions on Neural Networks · 1993
An adaptive image-coding system using neural networks is presented. The design of the system is based on the fact that system adaptability is a key to its effectiveness and efficiency. A composite source data model is suggested as a mathematical model for image data. Based on the composite source model, the coding system first classifies image data and then transforms and codes data classes with dedicated schemes. LEP, a reliable learning neural network model that uses experiences and perspectives, is proposed for image data classification using textures. A scheme for learning Karhunen-Loeve (K-L) transform basis arranged in the descent order with respect to eigenvalues in a two-layer linear-forward network is developed. These two learning mechanisms serve as essential parts of the coding system and enhance the adaptability of the system considerably. The experimental results show compressed images of good quality with bit rates as low as 0.1767 bit per pixel.