Informatics Publishing Limited

R. Kanchana ¹, R. Menaka ¹

Affiliations
1 School of Electronics Engineering, VIT University, Chennai – 600 127, Tamil Nadu, IN

Abstract

Computer ministered analysis is needed to diagnose nervous system diseases. Among the various human brain disorders ischemic stroke dominates and acts as the leading cause of death and frailty in most countries. A stroke occurs because of destruction of brain function due to the uproar in the blood stream to the brain. Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are the tests that processes and accounts the brains activity and plays very important role in detection and investigation of stroke. Various automated methods support well in discussing the normal and abnormal regions of brain. By visual inception it is hard to locate the critical changes in MRI and CT, thus inaugural up an immense research area for biomedical engineers to progress and contrivance numerous smart procedures for the identification of such subtle deviations. Hence computer aided detection scheme has to be developed to identify the normal and abnormal activity of the brain. This survey on stroke is to study such diagnostic system to outperform in bringing out the stroke lesions. Such automated methods using brain MRI and CT images to classify stroke activity tumors from non-tumor images greatly support researchers and doctors.

Keywords

Computer Aided Method, CT, Lesion, MRI, Stroke

Full Text

   

R. Menaka ¹, R. S. D. Wahida Banu ², B. Ashadevi ³

Affiliations
1 Anna University, Sarder Patel Road, Old Highways Building, Guindy, Chennai - 600 025, Tamil Nadu, IN
2 GEC, NH 7, Banglore Highways, Salem - 636011, Tamil Nadu, IN
3 CS Department, Kunthavai Nachiar Govt. Arts College for Women, Arulananda Nagar West Extension, Thanjavur -613007, Tamil Nadu, IN

Abstract

Web service is the technology tied up with SOAP, UDDI and WSDL of XML format, so web services searching based on XML keyword become essential. By systematic monitoring it has been observed that internet communication is less protected than intranet communication. The transaction exchange held through internet in web which is one among the distributed application is embodied to different vulnerability. In distributed environment, messages and data are exchanged as Extensible Markup Language (XML) format for its vast compatibility in transit. For facing the competitive environment, any business teams have to find their suitable web services among the bulk services prevails in market. In apt to this, survey has been made with different searching techniques and way to boost the security container filled with access permitted service alone. Our research work on XML based Web security is concentrated on providing the privacy, certification and integrity. We investigate the way to regulate and insist the security by applying XML Encryption and Signature for data or messages in transaction and in storage form. It also proves the performance improvement in searching data from vast resources, if so security constraint is provided. Search Engines Optimization (SEO) is enhanced with parsing the descriptive tags rather than chaos data. Traders need not have prior knowledge of web farms lifecycle and its protection.

Keywords

BPEL, Multi-Tier Security, User Satisfy Profile, Web Service, XML Cryptography

Full Text

   

Abhinav Arora ¹, R. Menaka ¹, Shivangi Gupta ¹, Archit Mishra ¹

Affiliations
1 Department of Electronics and Communication Engineering, VIT University, IN

Abstract

In this paper, the health of a plant is estimated using various non-destructive Image Processing Techniques. Chlorophyll content was detected based on colour Image Processing. The Haar transform is applied to get size of leaf and the parameters.

Keywords

Haar Transform, Chlorophyll, Decomposition, Gaussian Filter.

Full Text

     

Epuru Nithish Kumar ¹, Gaddam Manoj Kumar ¹, Gunda Venkatesh ¹, Tanguturi Sai Jaswanth ¹, R. Menaka ¹

Affiliations
1 Department of Electronics and Communication Engineering, VIT University, IN

Abstract

This paper presents a skin color model for face detection based on YCbCr Gauss model and KL transform. The simple gauss model and the region model of the skin color are designed in both KL color space and YCbCr space according to clustering. Skin regions are segmented using optimal threshold value obtained from adaptive algorithm. The segmentation results are then used to eliminate likely skin region in the gauss-likelihood image. Different morphological processes are then used to eliminate noise from binary image. In order to locate the face, the obtained regions are grouped out with simple detection algorithms. The proposed algorithm works well for complex background and many faces.

Keywords

KL Transform, Gauss Model, Statistical Model, Morphological Processing.

Full Text