Compression methods are important in many medical applications to ensure fast interactivity through large sets of images (e.g. volumetric data sets, image databases), for searching context dependant images and for quantitative analysis of measured data. Medical data are increasingly represented in digital form. The limitations in transmission bandwidth and storage space on one side and the growing size of image datasets on the other side has necessitated the need for efficient methods and tools for implementation. Many techniques for achieving data compression have been introduced. In this study we propose context based adaptive lossless image codec.(CALIC)(12)

International journal of electronics and communication engineering & technology (ijecet)

Matrix multiplication is widely used in a variety of applications and is often one of the core components of many scientific computations. This paper will examine three algorithms to compute the product of two matrices: the Naive, Strassen’s and Winograd’s algorithms. One of the main factors of determining the efficiency of an algorithm is the execution time factor, how much time the algorithm takes to accomplish its work. All the three algorithms will be implemented and the execution time will be calculated and we find that Winograd’s algorithm is the best and fast method experimentally for finding matrix multiplication. Deep Neural Networks are used for many applications. Training a Deep Neural Network is a time consuming process, especially when the number of hidden layers and nodes is large. The mechanism of Backpropagation Algorithm and Boltzmann Machine Algorithm for training a Deep Neural Network is revisited and considered how the sum of weighted input is computed. The process of computing the sum of product of weight and input matrices is carried out for several hundreds of thousands of epochs during the training of Deep Neural Network. We propose to modify Backpropagation Algorithm and Boltzmann Machine Algorithm by using fast Winograd’s algorithm. Finally, we find that the proposed methods reduce the long training time of Deep Neural Network than existing direct methods.

/pdf/winograd-s-inequality-effectiveness-for-efficient-training-w3u7rbyg8g.pdf

Winograd’s Inequality: Effectiveness for Efficient Training of Deep Neural Networks

Digital image and video image require large amount of capacity to store. Image compression means reducing the size of image, without losing its quality. Depending on the reconstructed image, to be exactly same as the original or some unidentified loss may be incurred, two techniques for compression exist. Two techniques are: lossy techniques and lossless techniques. Digital imaging play an important role in image processing therefore it is necessary to develop a system that produces high degree of compression while preserving critical image. In this paper we present hybrid model which is the combination of several compression techniques. This paper presents DWT and DCT implementation because these are the lossy techniques and also introduce Huffman encoding technique which is lossless. On several medical, Lena images simulation has been carried out. At last implement lossless technique so our PSNR and MSE will go better, and due to DWT and DCT we will get good level of compression without losing any image. When compared to standalone DCT and DWT algorithms,the proposed hybrid algorithm gives better result in term of peak-signal-tonoise ratio with a higher compression ratio.

Comparison and improvement of image compression using dct, dwt & huffman encoding techniques

Medical image segmentation is an initiative with tremendous usefulness. Biomedical and anatomical information are made easy to obtain as a result of success achieved in automating image segmentation. More research and work on it has enhanced more effectiveness as far as the subject is concerned. Several methods are employed for medical image segmentation such as Clustering methods, Thresholding method, Classifier, Region Growing, Deformable Model, Markov Random Model etc. This work has mainly focused attention on Clustering methods, specifically k-means and fuzzy c-means clustering algorithms .we have used the cluster centre initialisation algorithm in order the improve the performance of k-means and fuzzy C-means in addition with Kernelized fuzzy cmeans and Enhanced k means. Which has a better result in terms of silhouette score. The algorithms have been implemented and tested with Magnetic Resonance Image (MRI) images of Human brain. Results have been analyzed and recorded.

Medical image segmentation using enhanced k-means and kernelized fuzzy c- means

In this paper, we implemented a new model of image compression and decompression method to search the aimed image based on the robust image block variance estimation. Many methods of image compression have been proposed in the literature to minimize the error rate and compression ratio. For encoding the medium type of images, traditional models use hierarchical scheme that enables the use of upper, left, and lower pixels for the pixel prediction, whereas the conventional raster scan prediction methods use upper and left pixels. In this proposed work, we have implemented block estimation and image distortion rate to optimize the compression ration and to minimize the error rate. Experimental results show that proposed model gives a high compression rate and less rate compared to traditional models.

An optimized block estimation based image compression and decompression algorithm

Use of Digital Image Communication has increased exponentially in the recent years. Joint Photographic Experts Group (JPEG) is the most successful still image compression standard for bandwidth conservation. Evidently JPEG Compression system consists of a DCT transformation unit followed by a quantizer and encoder unit. At the decoder end, image is created by inverse DCT. In this paper, we present a set of new JPEG Compression algorithms that combines K-Means clustering algorithm and DCT to further reduce the bandwidth requirements. Experiments are carried out with many standard still images. Our algorithm identified to be giving almost same Peak Signal-to-Noise Ratio (PSNR) as the standard JPEG algorithm.

A novel k-means based jpeg algorithm for still image compression

Applications of Digital Image Communication have increased exponentially in the recent years. Evidently, discrete cosine transform (DCT) based algorithms are in wide use for reducing communication cost. Forward DCT and inverse DCT computation are reported to be taking very long time which may often impede real time responses in some applications. In this paper, we present Winograd’s matrix multiplication approach for forward DCT and inverse DCT computation to reduce their CPU time. Experiments are made with standard images and synthetic images.

Ch . Ramesh

Papers

A novel k-means based jpeg algorithm for still image compression

Fast dct algorithm using winograd's method