Yeshwantrao Chavan College of Engineering

About: Yeshwantrao Chavan College of Engineering is a based out in . It is known for research contribution in the topics: Inverter & Microstrip antenna. The organization has 632 authors who have published 586 publications receiving 4037 citations.

Retinal Blood Vessel Segmentation using combination of top-hat and h-maxima methods

Abstract: the diagnosis of retinal image is a basic and important concept for Diabetic Retinopathy detection and analysis. The important role play in digital retinal image is Vessel segmentation in diagnosis of various diseases. In this paper we have been working on most important portion which is segmentation of blood vessel. Blood vessels are segmented via top-hat and h-maxima methods and for classification Convolutional Neural Networks (CNN) technique can be used to get better accuracy. The network is trained in such a manner that it automatically segments the blood vessels and classify weather it is normal or abnormal. High-end graphics processor unit i.e. GPU system is used for training on largely available images and display the outputs, and this also works for high-level classification task. We have implemented this on two publicly available databases (DRIVE and STARE). The performance parameter involves during classification are accuracy, sensitivity, and specificity [4].

Local and Global Feature Fusion Based Visual Concept Detection in Images

Abstract: With the advent of digital cameras and mobile phones, advances in telecommunication and internet, millions of images are uploaded on the internet without much information about the image. An efficient method is necessary for automatic image annotation and indexing for the vast collection of images. Concept detection is task of detecting concepts present in image. In this paper, concept detection is obtained by effectively fusing local feature descriptors and global features descriptors. First object extraction is carried out using edge and color, and the aspect ratio of each extracted object is calculated. The local features of all extracted objects and global features of the image are computed. The detected concept of the query image is displayed based on the local and global feature matching scores obtained using our algorithm. The proposed algorithm is evaluated on Wang’s Corel dataset consisting of 1000 images. Results demonstrate that the proposed approach outperforms the KNN and ANN methods with high accuracy.

A Novel Approach to Extract Salient Regions by Segmenting Color Images with Hybrid Algorithm

Abstract: Due to the advent of computer technology image-processing techniques have become increasingly important in a wide variety of applications. This is particularly true for medical imaging such as Computer Tomography (CT), magnetic resonance image (MRI), and nuclear medicine, which can be used to assist doctors in diagnosis, treatment, and research. In this paper, hybrid algorithm for segmentation of color images is presented. The segments in images are found automatically based on adaptive multilevel threshold approach and FCM algorithm. Neural network with multisigmoid function tries to label the objects with its original color even after segmentation. One of the advantages of this system is that it does not require a past knowledge about the number of objects in the image. This Fuzzy-Neuro system is tested on Berkley standard image database and also attempts have been made to compare the performance of the proposed algorithm with other currently available algorithms. From experimental results, the performance of the proposed technique is found out to yields better extraction of salient regions with high resolution as nearly same as the original image and better than the existing techniques. It can be used as a primary tool to segment unknown color images. Experimental results show that its performance is robust to different types of color images.

Adiabatic Amplifier and Power Analysis of Different Adiabatic Inverters

Abstract: This paper proposes a new method of reducing the energy dissipation. Adiabatic logic style is proving to be an attractive solution for low power digital design. Many researchers have introduced different adiabatic logic styles in last few years and proved that these are better than CMOS. Adiabatic switching technique based on energy recovery principle is one of the innovative solutions at circuit and logic level to achieve reduction in power dissipation This paper mainly consist of implementation of Adiabatic amplifier and Basic Adiabatic inverters (ECRL,CAL,CPAL).Its comparative power analysis with conventional CMOS inverter is carried out. In this paper, we show that the power dissipation in adiabatic inverters is less as compared to CMOS inverter. All circuits are implemented using Chartered 0.35μm CMOS technology Tanner EDA 13.0 tool.

Design of control circuit for adaptive flash ADC

Abstract: This paper presents a proposed design of Peak Detector and Sub-Flash architecture for adaptive ADC. The control circuits are developed for Adaptive Resolution for Flash ADC. Peak detector circuits will consist of peak detector for variable resolution and sub-flash architecture for reconfigurability. The voltages from the Bias block are used to provide a control voltage for Peak Detector circuits. The Transient analysis for peak detector circuits are tested for pulse and sinusoidal input voltage and the settling time is reported to be 5ns and 10ns. For reconfigurability the vin is compared with Bias Block voltages for achieving the resolution i.e, 4 bit, 5 bit, 6 bit respectively.