Smitha J.C.,Lourdes College
Advances in Intelligent Systems and Computing | Year: 2015
A combined approach with MRI brain image denoising and abnormality detection process is proposed in this paper. The proposed technique is comprised of three stages, namely (i) image preprocessing, (ii) feature extraction, and (iii) image classification. Initially, in the preprocessing stage, denoising is performed on the input brain MRI image. The denoising process on the input image increases the accuracy of feature extraction stage. In feature extraction phase, the image features such as mean, variance, and multilevel 2D Haar wavelet decomposition are extracted for classifying the images in the database into normal and abnormal. By using these extracted features, the MRI brain images are classified by the well-known classification technique such as feed forward back propagation neural networks (FFBNN). The implementation of the proposed method shows improvements in classification of MRI images. © Springer India 2015.
Kumar S.S.,Noorul Islam Center for Higher Education |
Jojy C.,Lourdes College
Journal of the Indian Society of Remote Sensing | Year: 2016
Synthetic aperture radar (SAR) is a day and night, all weather satellite imaging technology. Inherent property of SAR image is speckle noise which produces granular patterns in the image.Speckle noise occurs due to the interference of backscattered echo from earth’s rough surface. There are various speckle reduction techniques in spatial domain and transform domain. Non local means filtering (NLMF) is the technique used for denoising which uses Gaussian weights. In NLMF algorithm, the filtering is performed by taking the weighted mean of all the pixels in a selected search area. The weight given to the pixel is based on the similarity measure calculated as the weighted Euclidean distance over the two windows. Non local means filtering smoothes out homogeneous areas but edges are not preserved. So a discontinuity adaptive weight is used in order to preserve heterogeneous areas like edges.This technique is called as discontinuity adaptive non local means filtering and is well-adapted and robust in the case of Additive White Gaussian Noise (AWGN) model. But speckle is a multiplicative random noise and hence Euclidean distance is not a good choice. This paper presents evaluation results of using different distance measures for improving the accuracy of the Non local means filtering technique. The results are verified using real and synthetic images and from the results it can be concluded that the usage of Manhattan distance improves the accuracy of NLMF technique. Non local approach is used as a preprocessing or post processing technique for many denoising algorithms. So improving NLMF technique would help improving many of the existing denoising techniques. © 2016 Indian Society of Remote Sensing
Chenthil Kumaran N.,Lourdes College |
Jebarajan T.,Raja Lakshmi Engineering College
International Journal of Applied Engineering Research | Year: 2015
Server replication is an approach that often used to ameliorate the scalability of service. One of the efficient factors in the efficient utilization of replicated servers is the ability to direct client request to the best servers according to some optimality criteria. It will amend performance and to move to data more proximate to the users. The conventional method for server replication is by means of Genetic Replication Algorithm. The GRA is much slower and the performance of this algorithm is most horrible. In this proposed research, an effective dynamic server replication with sophisticated precedence optimization algorithm has been proposed. In this system, the nodes are randomly grouped towards the servers and the servers are then filtered. The servers with higher priority are send to the optimization process, some optimization factors are used to optimize the best servers, and these optimized servers are replicated dynamically. The proposed system has been validated with the help of optimization algorithm and the experimental results demonstrated that the performance of the system are improved significantly. © Research India Publications.
Sekhar R.,Lourdes College |
Shaji R.S.,Noorul Islam University
International Journal of Digital Crime and Forensics | Year: 2014
Copy-Move forgery is the very prevalent form of image tampering. The powerful image processing tools available freely helps even the naive to tamper with images. A copy-move forgery is performed by copying a region in an image and pasting it in the same image most probably after applying some form of post-processing on the region like rotation, blurring, scaling, double JPEG compression etc. This makes it difficult to develop one common technique to detect copy-move forgery. As a result a considerable number of methods have been developed in view to detect different forms of copy-move forgeries. Those techniques can be classified generally as block based techniques and key- point based techniques. This paper presents an extensive survey on the very recent methods developed for copy-move forgery detection. Copyright © 2014, IGI Global.
Smitha J.C.,Lourdes College
International Review on Computers and Software | Year: 2014
The most necessary part of the living things which standardizes and manages other organs is the brain. The brain may get affected through any disease if the patient is not in a normal condition. Therefore it is significant to examine the condition of the brain. In the region of brain MRI image deformity fragmentation, various research works were made. However these research efforts presentations are needed in the image pre-analysis. During pre-analysis brain via MRI brain images for identifying the deformity, it is essential to examine the acquired patient's image in detail. An error treatment will be specified to the influenced patient if the study may have any error. So there is a necessity to develop precision in the deformity segmentation by achieving the fundamental pre-analysis in the MRI images. A combined approach with MRI brain image abnormality segmentation and denoising process is proposed in this paper. The proposed technique comprised of five stages namely, (i) Preprocessing, (ii) Feature Extraction, (iii) Image Classification, (iv) Segmentation and (v) Tissues Classification. Initially the database images are given to the preprocessing stage, for removing the noise. In preprocessing, the denoising process is performed it increases the segmentation and feature extraction accuracy. After the preprocessing, the image features are extracted to classify the images in the image database into normal and abnormal. After the image classification, the abnormal MRI images abnormal tissues like stroke, trauma and tumor are segmented. For this, the features are extracted from the segmented abnormal tissues. In the proposed technique, three features such as modified entropy, energy and innovative feature are extracted in the feature extraction stage. By using these extracted features, the abnormal tissues are classified by using a well known classification technique called Feed Forward Back Propagation Neural Network (FFBNN). The implementation results show the effectiveness of proposed MRI abnormality tissues segmentation technique in segmenting and classifying the MRI images and the achieved improvement in the segmentation and classification result. Furthermore, the performance of the proposed technique is evaluated by comparing with the existing MRI image segmentation techniques. © 2014 Praise Worthy Prize S.r.l. - All rights reserved.