Search

Copyright of Journal of Engineering Sciences & Information Technology is the property of Arab Journal of Sciences & Research Publishing (AJSRP) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Due to the fact that most of the application on EZT algorithm were applied on wavelet transformation. In the last ten years, the contourlet transformation shows that its efficiency is higher than the wavelet transformation due to its ability to deal with multidirections instead of the vertical and horizontal directions which are covered by the wavelet transformation. In this paper, the contourlet coefficient is adopted as inputs to the EZT (which normally are a wavelet coefficient ). Arranging the contourlet coefficient to be studied as input to EZT, the result of adopting modified contourlet coefficient was studied on two parameters (the file size and threshold value ) and tested by evaluating two factors (correlation and MSE). Comparing the result which we get it with the wavelet technique shows that the contourlet gives a result closer, to the original one depending on the correlation factor plus the PSNR factor. So, the proposed technique can be achieved.

This research developed a software which can be used for image compression. This research proposes two methods: the first uses Joint Photographic Experts Group (JPEG), while the second uses artificial neural network (Modified Fuzzy Adaptive Resonance Theory (MFART)) algorithm. This software is applied on two types of images (jpeg and tiff). Several parameters in compression methods are tested, the results reveal that the MFART is better than the JPEG metod. The Root Mean Square Error (ERMS) for MFART method on jpeg image is equal 3.7 but it is equal to 26.09 when JPEG method implement on to the same image. MATLAB has been used in the implementation of this software.

This research present four methods to compress digital images using clustering based on artificial intelligent techniques that include neural network, fuzzy logic and hybrid between them. To enhance the performance of the compression system, the first method was developed in two types (k-means 1 dimension run length encoding km1D, k-means 2 dimension run length encoding km2D) by applying traditional clustering algorithm k-means on color and gray level images and then apply compression algorithm RLE in one and two dimension by zigzag scanning to obtain compressed image. The second method (fuzzy c-mean 1dimension run length encoding fcm1D, fuzzy c-mean 2dimension run length encoding fcm2D) used fuzzy c-mean to apply clustering operation and then compression. The third method (kohonen 1 dimension run length encoding Koh1D, kohonen 2dimension run length encoding Koh2D) used kohonen neural network for clustering image and then used RLE. The fourth developed method (fuzzy kohonen 1dimension run length encoding fKoh1D, fuzzy kohonen 2dimension run length encoding fKoh2D) based on hybrid kohonen neural network and fuzzy logic i.e fuzzy kohonen network which is recognized as the best method among the four methods. The four compression methods that are implemented in this research are efficient when applied on gray level and color images.

The problem inherent to any digital image is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop algorithm that compress images to lower data rates with better quality. This research present, a new approach to image compression based on clustering. This new approach includes new objective function, and its minimization by energy function based on unsupervised two dimensional fuzzy Hopfield neural network. New objective function consists of a combination of classification entropy function and average distance between image pixels and cluster centers. After applying new method on gray scale sample images at different number of clusters, better compression ratio and signal to noise ratio was observed. The new method is also a new clustering analysis method, and it provides more compact and separate clustering.

In this paper, an efficient image compression algorithm for Bayer-pattern images is introduced. In Bayer pattern images each pixel is represented by 8-bit rather than 24-bit for colour images. The proposed algorithm separates the colour information from the Bayer-pattern image data before performing the compression operation. It partitions each colour plane into fixed size blocks. Each block is classified as a low or high intensity variation block using the standard deviation which compared against a predefined threshold. The low intensity variation blocks are encoded by its average while, the other blocks are encoded using the minimum, quantisation step and the bit plane. The quantisers that used in this paper are from 32 and 16 levels types. The effect of the block size on the output bit rate and image accuracy is studied. The results clarify that a good performance is achieved using 4×4-pixel blocks. Using 32 and 16 quantisation levels a bit rates of 1.8 to 5.2 bpp with a PSNR of 30 to 45 dB can be achieved for a range of thresholds 10 to 0.5.

This paper present a Resilient Backpropagation (RBP) algorithm based on hierarchical neural network for image compression. The proposed technique includes steps to break down large images into smaller blocks for image compression/ decompression process. Furthermore, a Linear Backpropagation (LBP) algorithm is also used to train hierarchical neural network, and both training algorithms are compared. A number of experiments have been achieved, the results obtained, are the compression rate and Peak Signal to Noise Ratio of the compressed/ decompressed images which are presented in this paper.

In this paper a modified LBG vector quantization alglrithm id presented and used with wavelet transform algorithm to compress the image. The modified LBG algorithm provides good representation for training vectors carrying important information which may repesent rare vectors in the training vectors. So this algorithm overcomes the problem of the traditional LBG algorithm that provides good representation for training vectors which occur frequently while rare vectors are not well represented. The use of the modified LBG algorithm with wavelet transform give better reconstructed image quality than the traditional LBG algorithm because the rare vectors hich carry important information are better represented. The two algorithm give the same compression ratio.

The vector quantization method for image compression inherently requires the generation of a codebook which has to be made available for both the encoding and decoding processes. That necessitates the attachment of this codebook when a compressed image is stored or sent. For the purpose of improving the overall efficiency of the vector quantization method, the need arose for improving a means for the reduction of the codebook size. In this paper, a new method for vector quantization is presented by which the suggested algorithm reduces the size of the codebook generated in vector quantization. This reduction is performed by sorting the codewords of the codebook then the differences between adjacent codewords are computed. Huffman coding (lossless compression) is performed on the differences in order to reduce the size of the codebbook.

Today there are a number of algorithms developed in the framework of international committees that allow still image compression. In this paper, the area of Vector Quantization (VQ) neural network with the Self-Organizing Feature Map (SOFM) has been compared with the ordinary vector Quantization technique Linde-Buzo-Gray (LBG) in image compression. The results were compared with the Back Propagation Neural Network BPNN which was employed to design a code book of an image to be compressed using VQ method. Results show that the neural technique gives a performance that is very close to optimal. The BPNN scheme not only has the advantage of the SOFM - VQ scheme but also improves the coded image quality. Experimental results are given and comparisons are made using the BPNN coding scheme and some other coding techniques. In the experiments, the BPNN coding scheme achieves the better visual quality about edge region and the best peak signal-to-noise ratio PSNR performance at nearly the same bit rate.

The problem inherent to any digital image is the large amount of bandwidth required for transmission or storage. This has driven the research area of image compression to develop algorithms that compress images to lower data rates with better quality. Artificial neural networks are becoming very attractive in image processing where high computational performance and parallel architectures are required.In this work, a three layered backpropagation neural network (BPNN) is designed to compress images using vector quantization technique (VQ).The results coming out from the hidden layer represent the codebook used in vector quantization, therefore this is a new method to generate VQ-codebook. Fast algorithm for backpropagation called (FBP) is built and tested on the designed BPNN. Results show that for the same compression ratio and signal to noise ratio as compared with the ordinary backpropagation algorithm, FBP can speed up the neural system by more than 50. This system is used for both compression/decompression of any image. The fast backpropagation (FBP) neural network algorithm was used for training the designed BPNN. The efficiency of the designed BPNN comes from reducing the chance of error occurring during the compressed image transmission through analog channel (BPNN can be used for enhancing any noisy compressed image that had already been corrupted during transmission through analog channel). The simulation of the BPNN image compression system is performed using the Borland C++ Ver 3.5 programming language. The compression system has been applied on the well known images such as Lena, Carena, and Car images, and also deals with BMP graphic format images.