Implementation of Fractal Image Compression Employing Hybrid Genetic-Neural Approach

摘要

This paper presents a hybrid approach of Genetic algorithm and back propagation based neural network (HGANN) for fractal image compression. One of the image compression techniques in the spatial domain is Fractal Image Compression (FIC) but the main drawback of FIC using traditional exhaustive search is that it involves more computational time due to global search. In order to improve the computational time and compression ratio, hybrid technique like HGANN has been proposed. Feature extraction reduces the dimensionality of the problem and enables the neural network to be trained on an image separate from the test image thus reducing the computational time. Lowering the dimensionality of the problem reduces the computations required during the search. The main advantage of neural network is that it can adapt itself from the training data. In order to reduce the complexity of having more training data, Genetic Algorithm (GA) has been incorporated into the neural network in order to obtain optimal values of weights and bias. Computer simulations reveal that the optimal values of weights for the network have been obtained and the network successfully classifies the domains correctly with minimum deviation which helps in encoding the image using FIC.