A competitive learning algorithm for non-zero memory codebook design in encoding of CT sequences

Implementation of Artificial Neural Network (ANN) in various aspects is increased day by day. One of the major applications is in compression of images. Here an algorithm has been developed for use in encoding of Computed Tomography (CT) image sequences. The method is based on application of ANN distributed system which classifies all possible m×m (here 4×4) blocks into a smaller number well distinct classes of vectors. In an extension of Kohonen self organising net called Frequency Sensitive Competitive Learning (FSCL) algorithm, the required time for obtaining an ignorable error will depend on both distortion and the number of iterations which, are more or less equal for all units. Application of ANN to Vector Quantisation (VQ) stems from this major concept that in usual methods the error between each input pattern and a pattern of the codebook (word), is calculated without regarding the weight of each pixel value in entire pattern. A proper ANN exploits this concept in an efficient classification of various patterns in an image and/or sequence of images. This significantly decreases artefact, such as blocking effect which normally appears in ordinary VQ reconstructed images in a low bitrate. In the case of sequences interframes correlation is exploited in provision of a common codebook for highly correlated frames. Further redundancy is decreased by optimal decomposition of the sequence into most correlated subsequences