Vinodpuri Gosavi - Academia.edu (original) (raw)

Papers by Vinodpuri Gosavi

Face recognition deals with the significant area of the ability of individual perception scheme a... more Face recognition deals with the significant area of the ability of individual perception scheme and is a monotonous process for various humans, while constructing a similar recognition prototype which is based on recognition of faces. The computational prototype doesn't only deals with the theoretical understandings but also deals with the various practical scenarios such as surveillance systems, controlling various accesses, human computer interface based designs, database management scenarios, criminal identification and also in other important real time applications. Recognition of the face is a fast mounting, inspiring and fascinating area in various recognitions based real time applications. Various efficient face recognition procedures are implemented and developed in last years. So this paper deals with the review of current terminologies and procedures used for automatic classifications of the faces with various variations in shapes and postures of faces.

International Journal of Advance Research, Ideas and Innovations in Technology, Mar 20, 2017

The Electrical metering instrument technology has come a long way from what it was more than 100 ... more The Electrical metering instrument technology has come a long way from what it was more than 100 years ago. From the original bulky meters with heavy magnets and coils, there have been many innovations that have resulted in size & weight reduction in addition to improvement in features and specifications. Resolution and accuracy of the meter have seen substantial improvements over the years. Introduction of the digital meter in the later part of last century has completely changed the way Electrical parameters are measured. Starting with Voltmeters & Ammeters, the digital meter has conquered the entire spectrum of measuring instruments due to their advantages like ease of reading, better resolution and rugged construction. Of particular significance is the introduction of the Electronic Energy Meter in the mid-eighties. Now a days, the energy consumption and energy distribution has become a big subject for discussion because of huge difference in energy production and consumption. In this regard, energy consumers are facing so many problems due to the frequent power failures; another important reason for power cuts is due to the unlimited energy consumption of rich people. In this aspect, to minimize the power cuts and to distribute the energy equally to all areas, some restriction should have over the power consumption of each and every energy consumer, and according to that the Government should implement a policy, by introducing Autonomous Energy Meters everywhere in domestic sector. Hence, the need has come to think on this line and a solution has to be emerged out.

International Journal of Scientific Research in Science and Technology

In this Present study, the technique of wavelet transform and neural network were developed for s... more In this Present study, the technique of wavelet transform and neural network were developed for speech based text-dependent and text0independent speaker identification. 390 feature were fed to feed-forward back propagation neural network for classification The function of feature extraction and classification are performed using wavelet and neural network system. The declared result shows that the proposed method can make an effective analysis with average identification rate reaching 98%. The best recognition rate selection obtained was for FFBPNN (Feed Forward Back Propagation Neural Network).

SSRN Electronic Journal, 2021

Now a days, the biometric system is playing a significant role, especially in the banking sector,... more Now a days, the biometric system is playing a significant role, especially in the banking sector, law enforcement region. In previous times the unimodal system was used for biometrics but now the trend is for multimodal biometrics which is an important part of pattern recognition and grabs a lot of attention of the people in the research area. A lot of work is done on unimodal systems but very less work is done on multimodal characteristics. This paper deals with the secure authentication process using fingerprint and face recognition multimodal systems for high classification accuracy and low error rates. The feature extraction and optimization are done using SIFT & PSO for the facial category and the ridges and minutiae extractions are done for the fingerprint. The proposed solution is evaluated on the Ollivati dataset for faces and the FVC200 dataset for fingerprints. From the result and discussions, it can be seen that the proposed approach can attain an accuracy of approximately 99.2% which is our desired objective, and low false acceptance and rejection rates which increases the authenticity of our multimodal system.

FR (Face Recognition) starts with feature extracting the co-ordinates of features like as a width... more FR (Face Recognition) starts with feature extracting the co-ordinates of features like as a width of wyes, pupil area and compare the consequence with the measurements deposited stored in the database and return the closest dataset in facial parameters. In current years, there are a lot of face recognition methods and techniques search and developed around the world. FR becomes an interesting research area and topic. It is established by several number of published papers regarded with FR add inf FE (Feature Extraction), FS (Feature Selection), Facial Algorithm Enhancements and Face recognition designs. The research work are to get the face recognition method (key points) given by the Scale and Localization by comparison with the existing work and algorithms. Feature Extraction using Scale Invariant Feature Extraction Algorithm. SIFT is significantly more effective strategy and extract the features in the form of key-points. Reduce the feature data using ant colony optimization algo...

International Journal of Scientific Research in Science and Technology, 2018

Face recognition has a wide range of possible applications from person identification and surveil... more Face recognition has a wide range of possible applications from person identification and surveillance to electronic marketing and advertising for selected customers. In facial recognition, there are different steps such as preprocessing, feature extraction and classification where feature extraction and classification are used to obtain maximum accuracy. In this research paper, different feature extraction techniques such as ASM, AAM, Gabor features, Template based, and several are critically reviewed. Apart from these, the different types of neural classification networks such as convolutional, backpropagation, radial basis function etc. in the domain of facial recognition are explored. The methods and algorithms developed in the current literature are studied and it is revealed that all the techniques are unique and have optimal performance. This research further makes a comparative analysis of these techniques based on their advantages and limitations.

2018 International Conference on Advances in Computing and Communication Engineering (ICACCE), 2018

International Journal of Advance Research, Ideas and Innovations in Technology, 2017

Electricity is one of the vital requirements for sustainment of comfort of life. It should be use... more Electricity is one of the vital requirements for sustainment of comfort of life. It should be used very judiciously for its proper utilization. The main purpose of this project is to measure the energy with high accuracy for industrial applications. In industry, There are lots of control panels in which the energy meters are used to measure the amount of energy consumed. Today with several manufacturers in the market , There are lots of parameters has to be considered like accuracy, cost, the size of meter etc. while designing the product. In the market, many types of energy meters are available for industrial applications but the high accuracy meters are not available that’s why it is the necessity of the market to propose an energy meter with high accuracy.

An image processing is an interesting topic to distinguish the human actions for overall life pre... more An image processing is an interesting topic to distinguish the human actions for overall life presentations. For instance, detecting the gesticulation of an individual when he or she is driving and warning him/her when he/she is in sleepy attitude will be fairly beneficial. Human motions can be recognized by detecting the dissimilar movements of iris, nose, mouth localization and pointers. In this research we are concentrating on the humanoid face for identifying appearance. Many practices are obtainable to distinguish face. In this paper, the main focus is given in the feature extraction approach and also the classification approach. The feature extraction is done by using principal component analysis and the classification is done by using Adaptive Neuro Fuzzy Inference System .

International Journal of Scientific Research in Science and Technology, 2020

Now a days Biometric recognition plays a vital role in issues associated with identification off ... more Now a days Biometric recognition plays a vital role in issues associated with identification off usurpation are currently at the heart of numerous concerns in our modern society. To work on connecting identity of an personality which is to be considered as an individual for various identification in the numerous operations of the state. Biometric authentication systems verify a person’s claimed identity from behavioral traits like signature, voice or physiological traits like face, iris, fingerprint , palm. Biometric system of identification and confirmation provides automatic recognition of an individual based on certain unique features or characteristics possessed by that individual. It takes into consideration the natural features of every single individual for various applications in today’s fast growing technical world. Biometric systems also help in overcoming the existing problems and limitations in authentication and identification fields and prove efficient and accurate in ...

International Journal of Electronics, Communications, and Measurement Engineering, 2019

Image processing has enormous applications and bio-metrics is one of them that has become a focal... more Image processing has enormous applications and bio-metrics is one of them that has become a focal point for researchers, as well as for developers. The most common application of bio-metrics is the face analysis. The face analysis is an efficient method to detect and verify the faces of people. In this research article we have the proposed techniques are CRC and KNN. Generally, CRC (Collaboration representation based classification) relies on the collaboration among various classes to represent an image sample. KNN (K-Nearest Neighbor) it is a category of classification approach that utilized to access regression purposes. The experiment is performed on the Yale database and the results are acquired from the simulation tool MATLAB. The performance parameters are accurate, processing time, random noise and random occlusion. A comparison of performance is described and it is proven that the proposed method results give the enhancement in the overall performance of face recognition and...

Face detection and recognition has many applications in a variety of fields such as security syst... more Face detection and recognition has many applications in a variety of fields such as security system, videoconferencing and identification. This document demonstrates how a face recognition system can be designed with artificial neural network using Eigen faces A face authentication system based on principal component analysis and neural networks is proposed to developed in this paper. The system consists of three stages; preprocessing, principal component analysis, and recognition. In preprocessing stage, normalization illumination, and head orientation were done. Principal component analysis is applied to find the aspects of face which are important for identification. Eigenvectors and eigenfaces are calculated from the initial face image set. New faces are projected onto the space expanded by eigenfaces and represented by weighted sum of the eigenfaces. These weights are used to identify the faces. Neural network is used to create the face database and recognize and authenticate the face by using these weights. In this work, a separate network was build for each person.