Time filter

Source Type

Chennai, India

Mredhula L.,Sathyabama University | Dorairangaswamy M.A.,AVIT
International Journal of Applied Engineering Research

Image Fusion is a process of combining common features of a set of images to get a output image with superior content in terms of subjective as well as objective analysis point of view. Main aim of this work is to present a review on some of the image fusion Techniques. A Comparison of all techniques are done fusing MRI and CT images and analysis is condudcted using various quality measures such as entropy, MSE, PSNR, SSIM, and BRISQUE. CT modalities provide information on denser tissues whereas MRI provides information on soft tissues. For medical applications CT and MRI images are fused for diagnostic purposes. © 2015, Research India Publications. Source

Venkatesh S.,Sathyabama University | Dorairangaswamy M.A.,AVIT
International Journal of Applied Engineering Research

Audio and image watermarking is one of the important and popular research areas for ownership protection of the media(image, audio, video etc) to prevent illegal distribution of the media and can also be used for media authentication, broadcast monitoring. A lot of work has been done on images, video watermarking, Audio watermarking as image and video use visual characteristics for watermark embedding, on the other hand, audio use human auditory system (HAS) properties for watermark embedding and watermark detection. A prior knowledge may not be available about various quantization steps that generate the maximum robustness and imperceptibility, thus DE is adopted in our watermarking scheme. In this paper, we propose a new method of DWT-DCT-SVD method are proposed using the DE algorithm to optimize the quantization. The time or frequency –scale modification leads to desynchronization and cause the false detection error, which should be avoided. For the synchronization problem, one way to solve it is to bind the watermark with the invariant audio features. With this method the watermark can be detected without synchronization error. Our scheme, the second way is used to address the desynchronization problem. Synchronization code is adopted in front of the watermark to orient the location of inserted watermark. DWT-DCT coefficients, are split into different segments, the segment length is obtained by dividing the length of the approximate coefficients by the watermark length. © Research India Publications. Source

Mredhula L.,Sathyabama University | Dorairangaswamy M.A.,AVIT
Journal of Medical Imaging and Health Informatics

An image is always subjected to noise corruption at the time of capturing and transmission. In this faster ultramodern age, visual data expressed as images serve as wonderful means of communication. Yet, it is an ill-fate that the image is usually transformed after transmission due to the interruption of noise. Therefore, noise removal has turned out to be a vital and widespread challenge in image processing. Pre-processing of received image is of major consideration, prior to using it beneficially in applications. Image denoising does the manipulation of image data to render finer quality visual image to the user. Hence, a method that can eradicate salt and pepper noise, Gaussian noise and Impulse noise from the image is being proposed. The denoising technique proposed here consists of two modules to simultaneously eliminate the noise from the images in an effective way. The first module employs pixel surge model (PSM) with probabilistic principal component analysis (PPCA) for image denoising. The second module attempts to enhance the image quality by applying filters like morphological filter and region props on the results of probabilistic principal component analysis. The overall result of denoising that is produced with the proposed method is compared against the previously known method for illustrating the system effectiveness. © 2016 American Scientific Publishers All rights reserved. Source

Beulah David D.,Sathyabama University | Dorairangaswamy M.A.,AVIT
Journal of Chemical and Pharmaceutical Sciences

This paper proposes a system for finding changes in satellite images taken at two different intervals of time and it may be some years or occurrences of images before and after flooding etc.,. The changes are obtained as binary labels (changed/unchanged) for each pixel. The input images may be of monochromatic or color images and also these images may be of various graphic file formats like PNG, BMP, JPG etc.,. The RGB images are converted to gray images. The mean ratio and log ratio are obtained from both input images. These are fused together to form a difference image using Discrete Wavelet Transform (DWT). A fuzzy clustering approach is applied to classify both changed and unchanged regions in the difference image. Previously this system is done using Fuzzy Local Information C means clustering. To enhance the changed information and to reduce the effect of noise, the spatial contextual information is added along with the self data information using Reformulated Fuzzy Local Information C-means Clustering (RFLICM). The resultant change detected images are showing good performance than the existing techniques. The performance measures are compared using Percentage of Correct Classification (PCC) and Kappa statistic parameter which gives the measure of accuracy for FLICM and RFLICM. Experimental results are compared for different dimensions of satellite images with different file formats taken at different intervals of time and the computation time is also found out. Source

Kalavathy R.,AVIT | Suresh R.M.,SMIT
Journal of Chemical and Pharmaceutical Sciences

Electronic medical records form a major source of information regarding a patient's health history. Governments in the present take necessary steps to gather the patient's health history to carry out research and be prepared for any disease outbreaks at large to the citizens. Research has shown that the disease outbreaks are due to the lifestyle, the living conditions and the treatment undergone during the past. Medical literature states that many drugs whose complete safety profile unknown have been approved. Some drugs have shown serious adverse events (SAE), and subsequently withdrawn. There may be some drugs which still show adverse effects on the patients. This work makes an attempt to extract details regarding the drug administration from the electronic medical records (EMR) and employ the Bayesian classifier to find any SAE. It also analyses the various data mining techniques to find adverse events. The main advantage in using EMR is that they can be enhanced with powerful classification algorithms that can deal with images also. Source

Discover hidden collaborations