Entity

Time filter

Source Type


Kande G.B.,Vasireddy Venkatadri Institute of Technology | Savithri T.S.,Jawaharlal Nehru Technological University | Subbaiah P.V.,Amrita Sai Institute of Science and Technology
Journal of Digital Imaging | Year: 2010

An efficient approach for automatic detection of red lesions in ocular fundus images based on pixel classification and mathematical morphology is proposed. Experimental evaluation of the proposed approach demonstrates better performance over other red lesion detection algorithms, and when determining whether an image contains red lesions the proposed approach achieves a sensitivity of 100% and specificity of 91%. Copyright © 2010 by Society for Imaging Informatics in Medicine. Source


Subbaiah P.V.,Amrita Sai Institute of Science and Technology | Savithri T.S.,Jawaharlal Nehru Technological University
Journal of Medical Systems | Year: 2010

Performing the segmentation of vasculature in the retinal images having pathology is a challenging problem. This paper presents a novel approach for automated segmentation of the vasculature in retinal images. The approach uses the intensity information from red and green channels of the same retinal image to correct non-uniform illumination in color fundus images. Matched filtering is utilized to enhance the contrast of blood vessels against the background. The enhanced blood vessels are then segmented by employing spatially weighted fuzzy c-means clustering based thresholding which can well maintain the spatial structure of the vascular tree segments. The proposed method's performance is evaluated on publicly available DRIVE and STARE databases of manually labeled images. On the DRIVE and STARE databases, it achieves an area under the receiver operating characteristic curve of 0.9518 and 0.9602 respectively, being superior to those presented by state-of-the-art unsupervised approaches and comparable to those obtained with the supervised methods. © 2009 Springer Science+Business Media, LLC. Source


Telia E.D.,Noble College | Taherunnisa M.,Noble College | Deepthi G.K.,Amrita Sai Institute of Science and Technology | Choragudi B.M.,Sujay Bio Technology Pvt. Ltd. | Choragudi B.R.,Noble College
Rasayan Journal of Chemistry | Year: 2011

The oxidative coupling of the proposed method is simple, rapid and sensitive with reasonable precision and accuracy. The precision of the method was found by analyzing a set of eight solutions, each containing a final concentration value approximately in the middle of die Beer's law range. The percent relative standard deviation in method is presented in Table-2. The accuracy of the method was determined by taking different known amounts (within Beer's law limits) of the drug and analyzing them by proposed method. The results are given in Table - 3. In the determination of tetracyclines the excipients usually present in formulations (glucose, starch, sodium hexaphosphate and some vitamins) and the other antibiotics such as cycloserline, streptomycin lidocaine or penicillins did not interfere. © 2011 RASAYAN. All rights reserved. Source


Rama Krishna Y.,PVP Siddhartha Institute of Technology | Krishna Prasad P.E.S.N.,PVP Siddhartha Institute of Technology | Subbaiah P.V.,Amrita Sai Institute of Science and Technology | Prabhakara Rao B.,Jawaharlal Nehru Technological University Kakinada
Lecture Notes in Electrical Engineering | Year: 2013

Smart Antenna is a device that enables to steer and modify an arrays beam pattern to enhance the reception of a desired signal, while simultaneously suppressing interfering signals through complex weight selection. The weight selection process is a complex method to get low Half Power Beam Width (HPBW) and Side Lobe Level (SLL). The aim of this task is to minimize the noise and interference effects from external sources. This paper presents a Hybrid based model for Smart Antennas by combining CLMS and Augmented CLMS algorithms. Since CLMS and ACLMS models have their own pros and cons in the process of adaptive beam forming, Hybrid model results a better convergence towards desired signal, Low HPBW and low SLL in the noisy environment. © 2013 Springer Science+Business Media. Source


Hemanja G.,Andhra University | Satya Prasad K.,Andhra University | Venkata Subbaiah P.,Amrita Sai Institute of Science and Technology
International Journal of Signal and Imaging Systems Engineering | Year: 2015

The digital spectral analysis is of prime consideration for effective reception and analysis of signals with improved spectral characteristics with simple techniques. For this purpose, this paper presents a novel technique in digital bandpass filter bank by Modified Kaiser window based finite impulse response method in multirate processing. The finite impulse response method results in better passband and stopband response in addition to precise control over phase response. This novel technique is more effective in the proposed method in the sense that it allows the modification of samples of input signal in order to derive the advantages in respect of selectivity, stopband attenuation, peak output apart from smooth response in spectral output as compared to the existing methods. Further, with improved features of passband characteristic and spectral efficiency, the proposed method of spectral analysis is better suitable for most of real-time applications, especially in digital hearing aids. © Copyright 2015 Inderscience Enterprises Ltd. Source

Discover hidden collaborations