Nānded, India
Nānded, India

Time filter

Source Type

ICWET 2010 - International Conference and Workshop on Emerging Trends in Technology 2010, Conference Proceedings | Year: 2010

The field of image compression is concerned with removing the spatial and temporal redundancies present in an image sequence to more efficiently and concisely store and transmit the information. Traditional methods rely on waveforms or transform coding to reduce the spatial correlation and block based motion compensation to reduce the temporal correlation in an image sequence. To achieve the significant reduction in bandwidth needed for the next generation technology, more sophisticated models utilizing the structure inherent in an image sequence are required. In order to be used effectively however, video is often compressed for storage and transfer, and then decompressed for use. Generally these types of work face additional challenges of meeting two inherently conflicting requirements; reducing the transmission bit-rate at the same time increasing the image quality. This paper explores the details of implementing a very low bit rate video coding system (JPEG based architecture) with scalable bit rate vs. video quality for video-telephony, video-conferencing, and video streaming to mobile phones for a limited bandwidth application. Copyright 2010 ACM.

International Conference and Workshop on Emerging Trends in Technology 2011, ICWET 2011 - Conference Proceedings | Year: 2011

This project aims at low bit rate videos. There are various techniques available like MPEG 4, WMV, and H.264/AVC which does the same. In this project H.264/AVC has been modified to further reduce the bit rate of the videos. Quality lowers down a bit but the bit rate which is of utmost important criteria for the limited bandwidth factor is achieved. Copyright © 2011 ACM.

Vipparthi S.K.,Malaviya National Institute of Technology, Jaipur | Murala S.,Indian Institute of Technology Ropar | Gonde A.B.,SGGSIET | Wu Q.M.J.,University of Windsor
IET Computer Vision | Year: 2016

This study proposes a new feature descriptor, local directional mask maximum edge pattern, for image retrieval and face recognition applications. Local binary pattern (LBP) and LBP variants collect the relationship between the centre pixel and its surrounding neighbours in an image. Thus, LBP based features are very sensitive to the noise variations in an image. Whereas the proposed method collects the maximum edge patterns (MEP) and maximum edge position patterns (MEPP) from the magnitude directional edges of face/image. These directional edges are computed with the aid of directional masks. Once the directional edges (DE) are computed, the MEP and MEPP are coded based on the magnitude of DE and position of maximum DE. Further, the robustness of the proposed method is increased by integrating it with the multiresolution Gaussian filters. The performance of the proposed method is tested by conducting four experiments onopen access series of imaging studies-magnetic resonance imaging, Brodatz, MIT VisTex and Extended Yale B databases for biomedical image retrieval, texture retrieval and face recognition applications. The results after being investigated the proposed method shows a significant improvement as compared with LBP and LBP variant features in terms of their evaluation measures on respective databases. © The Institution of Engineering and Technology 2016.

Manthalkar R.,SGGSIET
ACM International Conference Proceeding Series | Year: 2010

Rapid development of the multimedia and the associated technologies urge the processing of a huge database of video clips. The processing efficiency lies on the search methodologies utilized in the video processing system. Usage of inappropriate search methodologies may make the processing system ineffective. Hence, an effective video retrieval system is an essential pre-requisite for searching relevant videos from a huge collection of videos. In this paper, an effective content based video retrieval system based on some dominant features such as motion, color and edge is proposed. The system is evaluated using the video clips of format MPEG-2 and then precision-recall is determined for the test clip. © 2010 ACM.

Kamble D.N.,AVCOE | Nandedkar V.M.,SGGSIET
Applied Artificial Intelligence | Year: 2010

The connecting rod is among the most important part used in various engines. With increasing demand for geometrical dimensional accuracy and internal quality, the forging of connecting rod is under investigation. The study deals with an analytical approach in regard to design of knowledge base of an expert system for forging connecting rods. The proposed analytical relations are based on the SLAB method modified by introducing the temperature-dependent flow stress and empirical set of relations for flash dimensions. The overall approach is designed to predict the flash load and cavity load contribution to total load. The cavity stress, flow stress, and principal stresses are also predicted at three different sections of the connecting rod with respect to temperature. The obtained results are verified by a literature comparison and are validated by conducting experiments. The expert system is designed based on the application of VISUAL BASIC language. Copyright © 2010 Taylor & Francis Group, LLC.

Wankhade K.,G.H. Raisoni College of Engineering | Rane D.,G.H. Raisoni College of Engineering | Thool R.,SGGSIET
Proceedings - 2013 International Conference on Communication Systems and Network Technologies, CSNT 2013 | Year: 2013

Feature selection, the process of removing irrelevant features can be extremely useful in reducing the dimensionality of the data to be processed, in reducing execution time and improving predictive accuracy of the classifier. It is very hard to process over the large data set with respect to the time, memory and the computation cost. Because the bigger size data set are having the large number of the attributes to process, it is not necessary in many cases that all the features are relevant to get the knowledge about the domain. We want to decrease the number of features to process for classification. © 2013 IEEE.

Vipparthi S.K.,Malaviya National Institute of Technology, Jaipur | Murala S.,Indian Institute of Technology Ropar | Nagar S.K.,Banaras Hindu University | Gonde A.B.,SGGSIET
Neurocomputing | Year: 2015

In this paper, a new coding scheme, local Gabor maximum edge position octal patterns (LGMEPOP) is proposed for content based image retrieval. The standard local binary pattern (LBP) collects the sign edge (binary code) information between the center pixel and its surrounding neighbors in an image. Further, the concept of LBP is extended to local maximum edge binary pattern (LMEBP) which collects the sign code (binary code) using the magnitude edges. These magnitude edges are collected based on the maximum edges between the center pixel and its surrounding neighbors in an image. In this paper, we propose a new feature descriptor, octal code which is coded based on the maximum edge positions (MEP) on Gabor responses. Specially, each pixel of every Gabor response gains eight edges based on the relationship between the referenced pixel and its neighbors. LGMEPOP utilizes the first three dominant (maximum) edge positions in an octal code generation. Then, these three maximum edge positions are encoded into three-eight octal numbers to produce the LGMEPOP. Further, the LGMEPOP is classified into two categories which are named as sign maximum edge position octal pattern (SMEPOP) and magnitude maximum edge position octal pattern (MMEPOP). The SMEPOP and MMEPOP are coded based on the sign and magnitudes of dominant edges respectively. The performance of the proposed method is tested on two benchmark databases. The results after being investigated show a significant improvement as compared to other existing methods (LBP and LBP variants) in terms of average retrieval precision (ARP) and average retrieval rate (ARR) on Corel-5000 and Corel-10000 databases. © 2015 Elsevier B.V.

11th IEEE India Conference: Emerging Trends and Innovation in Technology, INDICON 2014 | Year: 2015

In this paper new technique called 'KITE' is implemented for brain tumor growth analysis. This is done by using gray images pixel count inside kite shape boundaries. We also differentiated gray color shades to focus over the outgrowth of tumor. As we know in medical field, countless radiological and pathological images in advanced organization are developed commonly in clinics and medical focuses with refined picture securing gadgets and computerized scanners. Medical images are for the most part intricate in nature and are utilized for diagnosis, therapy, exploration and training. Our implemented KITE technique proves the most cost effective and high precision application for detection of brain tumor. © 2014 IEEE.

Shaikh N.F.,College of Engineering, Pune | Doye D.D.,SGGSIET
Journal of Intelligent and Fuzzy Systems | Year: 2016

Iris Recognition that emerged two decades back has a number of algorithms developed and vast amount of work has been carried out since its inception. Iris recognition uses pattern-recognition techniques based on high-resolution images of the person. This paper proposes a novel iris recognition system using FFBNN-ACFO. Initially the given input images are preprocessed using adaptive median filter to remove noise. Then the features which are extracted from the preprocessed image are used to train the FFBNN. During training, FFBNN parameters are optimized by ACFO to get high recognition accuracy. In the testing phase sufficient number of iris images, are utilized to analyze the performance of the proposed iris recognition system. The results of the proposed method are compared with FFBNN-AAPSO, FFBNN-PSO, and FFBNN techniques. The comparison result shows that the proposed iris recognition system based on FFBNN-ACFO, gives higher recognition accuracy than the existing iris recognition systems. © 2016 -IOS Press and the authors. All rights reserved.

Singh A.R.,S.G.G.S.I.E.T | Dambhare S.S.,College of Engineering, Pune
International Journal of Electrical Power and Energy Systems | Year: 2013

In this paper, the analytical and simulation results of the application of adaptive distance protection scheme for the transmission line incorporating Static Var Compensator (SVC) connected at the mid-point is presented. The mal-operation of the distance protection for the transmission line with SVC at various locations are studied. The simulation results show the under-reaching and over-reaching is more severe with SVC at mid-point of the transmission line. To mitigate the mal-operation of the distance protection, the adaptive scheme is presented based on recursive simulation study. The simulation result with adaptive scheme is outperformed as compared with the conventional scheme. Electro-magnetic Transient Program (EMTP) simulations on two machine system is used to substantiate the claim. © 2013 Elsevier Ltd. All rights reserved.

Loading SGGSIET collaborators
Loading SGGSIET collaborators