Using Artificial Intelligence Techniques for Image Compression

Abstract

Image compression helps in storing the transmitted data in proficient way by decreasing its redundancy. This technique helps in transferring more digital or multimedia data over internet as it increases the storage space. This research presents some methods to compress digital images using Artificial Intelligence Techniques(AITs) that include from fuzzy logic, swarm intelligent technique, and artificial neural networks. Traditional clustering algorithm k-means and AITs were used, such as Gath-Geva fuzzy clustering algorithm, and Particle Swarm Optimization Technique(PSO), and combined Gath-Geva with backpropagation neural network to produce a new method which is called Fuzzy BackPropagation Network (FBPN) algorithm, by applying these methods on gray level and color images and then applying compression algorithm RLE on it to obtain compressed image. Image quality measures have done by Peak Signal to Noise Ratio(PSNR), Mean Square Error(MSE), and Bitperpixel(bpp), compression ratio (CR) have been computed. Finally, a comparison between results after applying these algorithms on the images data set was obtained.

Keywords

• k-means algorithm, gath-geva (gg) fuzzy clustering algorithm
• particle swarm optimization technique(pso)
• fuzzy backpropagation neural network (fbpnn)