Vinayak Ashok Bharadi

Vinayak Ashok Bharadi

Auto-generated profile, based on publicly available information

Vinayak Ashok Bharadi

TCET, Mumbai University, Mumbai, India

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2018
Verified
Conference Paper
Closed access
Bhavesh PandyaBhavesh Pandya
Bhavesh Pandya
Georgina CosmaGeorgina Cosma
Georgina Cosma
AAAli A. Alani
Ali A. Alani
ATAboozar Taherkhani
Aboozar Taherkhani
VBVinayak Bharadi
Vinayak Bharadi
TMT.M McGinnity
T.M McGinnity
Biometric systems detect authenticity based on users' distinct physiological or behavioral characteristics for purposes of identification and access control. These pattern recognition systems are difficult to bypass when compared to traditional token or password based systems. This paper is proposing a new deep learning architecture for fingerprint recognition. The proposed architecture comprises of a pre-processing stage for extracting texture features from fingerprints, and this stage is performed by using histogram equalization, Gabor enhancement and fingerprint thinning. The pre-processed fingerprints are input into a Deep Convolutional Neural Network classifier. The proposed approach has achieved 98.21% classification accuracy with 0.9 loss. The obtained accuracy is significantly higher than previously reported results on the same dataset, 77%.

1 February 2015
Verified
Conference Paper
Closed access
VBVinayak Ashok Bharadi
Vinayak Ashok Bharadi
GDGodson Michael Dsilva
Godson Michael Dsilva
The signature recognition systems are widely used and measure of security and authenticity in terms of commercial as well as official transactions. The exciting signature recognition systems need a high configuration machine to perform multiple operations of feature vector extraction, enrollment and verification. These implementations are generally standalone and implemented on a single server based architecture, in this case even a single point of failure may occur. The standalone application are not scalable. With the increasing number users the biometric implementation has to be scalable and capable of handling large datasets for a large population. In this paper, a highly scalable, pluggable and faster cloud based online signature recognition system is proposed, which is capable of operating on enormous amounts of data, which, in turn, induces the need for sufficient storage capacity and significant processing power.

1 September 2014
Verified
Conference Paper
Closed access
VBVinayak Ashok Bharadi
Vinayak Ashok Bharadi
Bhavesh PandyaBhavesh Pandya
Bhavesh Pandya
BNBhushan Nemade
Bhushan Nemade
Biometric systems are based on capturing human bodily features and using them for authentication. Depending on single or multiple biometric traits used for authentication, unimodal or multimodal biometric systems can be implemented. Human iris & fingerprints have unique texture pattern and this can be used for identifying the person. In this paper a multimodal biometric system based on iris and fingerprint is proposed. Texture feature extraction using Hybrid wavelets is done. Fingerprint & Iris features are extracted using multilevel decomposition of captured sample image using a new family of wavelet called Hybrid wavelet. In this paper KNN classifier used for unimodal fingerprint recognition and multi-instance iris recognition. Feature vector of iris and fingerprint are combined using decision fusion technique. The FAR-FRR analysis is performed and the results suggests that the Hybrid Wavelets are having good texture feature extraction ability and proposed system has achieved up to 77% correct classification ration.

1 January 2016 in Procedia Computer Science
Verified
Journal Article
Open access
VKVikas Kaul
Vikas Kaul
BNBhushan Nemade
Bhushan Nemade
VBVinayak Bharadi
Vinayak Bharadi
SKS.K. Narayan Khedkar
S.K. Narayan Khedkar
This paper presents design, implementation, evaluation and comparison of security enhancements in data transmission for next generation encryption highlighting the possible weaknesses within the current AES encryption algorithm. An enhanced encryption method with AES algorithm is used here within TLS. Enhancement is done in AES by first using chaos and then modifying the S-box .The use of chaos sequence makes the key space infinite and the static S-box is made dynamic using cipher key. To increase the complexity of the system, AES is integrated in Round structure. The evaluation focuses on: Encryption- Decryption time, Throughput-speed and Avalanche effect. Results show that speed of around 2Mbps is achieved which is compatible with LTE networks. Also performance evaluation of traditional AES and enhanced AES do not show much deviation and hence enhanced version can be a good alternative. More attack resistance and complexity is achieved by integrating AES in a Round structure which gives non linearity to the system .The number of rounds in the enhanced system can be made variable as shown in the results and can be application specific to achieve the desired throughput and speed making the system more compatible current and next generation networks

25 February 2010 in International Journal of Computer Applications
Verified
Journal Article
Closed access
HKH B Kekre
H B Kekre
VBV A Bharadi
V A Bharadi

25 February 2010 in International Journal of Computer Applications
Verified
Journal Article
Closed access
HKH B Kekre
H B Kekre
VBV A Bharadi
V A Bharadi