A Cellular Connectionist Architecture for Clustering-Based Adaptive Quantization with Application to Video Coding

This paper presents a novel cellular connectionist model for a clustering-based adaptive quantization for video coding applications. The adaptive quantization is designed for a wavelet-based video coding system with the desired scene adaptive and signal adaptive quantization because of its ability to differentiate whether a specific coefficient is part of the scene structure through Gibbs random field constraints. The adaptive quantization is accomplished through an MAP estimation based clustering process whose massive computation of neighborhood constraints makes it difficult for a real-time implementation of video coding applications. The proposed cellular connectionist model aims at designing an architecture for the real-time implementation of the clustering-based adaptive quantization. With a cellular neural network architecture mapping onto the image domain, the powerful Gibbs spatial constraints are realized through interactions among neurons connected with their neighbors. In addition, the computation of coefficient distribution is designed as an external input to each component of a neuron or processing element (PE). We prove that the proposed cellular neural network does converge to the desired steady state with proposed update scheme. This model also provides a general architecture for image processing tasks with Gibbs spatial constraint-based computations.