Image compression is one of the important research fields in image processing. Up to now, different methods are presented for image compression. Neural network is one of these methods that has represented its good performance in many applications. The usual method in tr More
Image compression is one of the important research fields in image processing. Up to now, different methods are presented for image compression. Neural network is one of these methods that has represented its good performance in many applications. The usual method in training of neural networks is error back propagation method that its drawbacks are late convergence and stopping in points of local optimum. Lately, researchers apply heuristic algorithms in training of neural networks. This paper introduces a new training method based on the Gravitational Search Algorithm. Gravitational Search Algorithm is the latest and newest version of swarm intelligence optimization approaches. In this algorithm, the candidate answers in search space are masses that interact with each other by gravitational force and change their positions. Gently, the masses with better fitness obtain more mass and effect on other masses more. In this research, an MLP neural network by GSA method is trained for images compression. In order to efficiency evaluation of the presented compressor, we have compared its performance toward PSO and error back propagation methods in compression of four standard images. The final results show salient capability of the proposed method in training of MLP neural networks.
Manuscript profile
One of the important research areas in image processing is image compression. Until now, various methods for image compression have been presented, among which neural networks have attracted many audiences. The most common training method of neural networks is the error More
One of the important research areas in image processing is image compression. Until now, various methods for image compression have been presented, among which neural networks have attracted many audiences. The most common training method of neural networks is the error backpropagation method, which converges and stops at local optima are considered one of its most important weaknesses. The researchers' new approach is to use innovative algorithms in the process of training neural networks. In this article, a new educational method based on gravity search method (GSA) is introduced. The gravity search method is the latest and newest version of all types of collective intelligence search and optimization methods. In this method, the candidate answers in the search space are objects that are affected by the force of gravity and their positions change. Gradually, objects with better fit have more mass and have a greater effect on other objects.
In this research, an MLP neural network is trained for image compression using the GSA algorithm.
Manuscript profile
