Jenkin Winston

RESEARCH INTERESTS

Image Analysis using machine learning and deep learning

Scopus Publications

A miniaturized uniplanar MIMO antenna for n79/n46/millimeter-wave applications
Jeevitha Joseph, Gunamony Shine Let, Chandran Benin Pratap, and J Jenkin Winston
Wiley
This research suggests a compact uniplanar multiple‐input multiple‐output (MIMO) with four ports for n79/n46/millimeter‐wave (mm‐wave) applications. The size of the quad MIMO is only 30 × 30 × 0.8 mm3. MIMO system consists of four identical Z‐shaped radiators and common ground on the same plane and no decoupling structures are used for isolation. The system covers the bandwidth of 1.9 GHz (4.4–6.3 GHz) with a mid‐frequency of 5.6 GHz and also covers the high‐band frequencies ranging from 18 to 30 GHz with a bandwidth of 12 GHz. The suggested quad MIMO is fabricated on an FR‐4 board, and the measured outcomes are well in line with the simulated results. An isolation value of −11 dB has been achieved for mid‐band frequency and −24 dB has been attained for mm‐wave bands. Through the value of DG = 10 dB, ECC < 0.07, TARC < −3 dB, MEG < −5 dB, and the ratio of MEG = 1 dB, uniplanar quad MIMO shows acceptable MIMO diversity performance. The entire system was evaluated for the users' hand specific absorption rate (SAR) impacts and is within the limits. After the complete analysis of the miniature quad MIMO antenna, an 8‐port, and a 16‐port uniplanar MIMO are simulated for smartphone‐sized dielectric substrates and the performances were examined. The suggested MIMO system provides an efficient single‐layer MIMO antenna to 5G smartphones with high bandwidth and low SAR. The proposed quad MIMO systems are suitable for both the sub‐6 GHz band and the mm‐wave band.


Effective Detection of Copy Move Forgery Using Surf
R A Rakhi, Aldin Justin Sundararaj, R. Catherine Joy, and J. Jenkin Winston
IEEE
Copy move forgery is a technique for altering digital images by copying and pasting contents from the original image into different parts of the same image. It is of great importance to detect tampering as the credibility of digital images are being lost. Keypoint based methods proved to be efficient in localizingforgery. The proposed method uses SURF for feature extractionand improved forgery localization method for efficiently localizing forgery. Finally, comparison with the existing keypoint based methods to prove the efficiency of forgery localization in digital images. The tampered image is displayed as binary image for better understanding. The proposed methods efficiently localize forgery even if the tampered region is rescaled, rotated or blurred. The performance is validated by TPR, FPR and F1 score and comparing the same with the existing methods.


Hybrid deep convolutional neural models for iris image recognition
J. Jenkin Winston, D. Jude Hemanth, Anastassia Angelopoulou, and Epaminondas Kapetanios
Springer Science and Business Media LLC



Vulnerabilities and Ethical Issues in Machine Learning for Smart City Applications
K. Martin Sagayam, Roopa Jeyasingh, J. Jenkin Winston, and Tony Jose
Springer International Publishing



Combination of thermal and sRGB imaging techniques for advanced surveillance system
K. Martin Sagayam, J. Jenkin Winston, Mohd Helmy Abd Wahab, Bharat Bhushan, Radzi Ambar, and Hazwaj Mhd Poad
International Association for Educators and Researchers (IAER)
Surveillance is described as close observation; this term is used mostly when it comes to security observations and recording. Nowadays in our daily life we see the need of security rising up with the constant increase in the world of technology and features. On the other hand, the industries and firms continuously face threats and are pushed to a situation of seeking help for their safety. Also, that there are various blind spots in the regular security cam even the operator is not in a position to identify an emergency or any such need. This work is focused on providing clarity to such issues to the respective personal. It might be an industry, an office workspace, a supermarket or even a house. This concept deals with the enhancement of the surveillance system by infusing two different frames of Thermal and sRGB obtained input and give the output of noise reduced, enhanced and more visible image.


Performance-enhanced modified self-organising map for iris data classification
J. Jenkin Winston and D. Jude Hemanth
Wiley
Biometric systems are widely used in applications such as forensics and military. Biometric authentication is a challenging and complex task. These biometric systems must be accurate for practical applications. In this era of artificial intelligence, artificial neural network‐based classifiers are widely used in biometric‐based systems. However, most of the artificial neural network‐based classifiers are less accurate and computationally complex. In this work, two modified self‐organising map (SOM) networks are proposed for iris image classification to improve the performance measures. Particle swarm optimization technique is used in the training process of conventional SOM. The experiments are carried out with conventional and modified classifiers. The proposed modified classifiers provide better performance than the conventional SOM classifier.


Novel optimization based hybrid self-organizing map classifiers for iris image recognition
J. Jenkin Winston, Gul Fatma Turker, Utku Kose, and D. Jude Hemanth
Springer Science and Business Media LLC
The concern over security in all fields has intensified over the years. The prefatory phase of providing security begins with authentication to provide access. Inmany scenarios, this authentication is provided by biometric systems.Moreover, the threat of pandemic hasmade the people to think of hygienic systemswhich are noninvasive. Iris image recognition is one such noninvasive biometric system that can provide automated authentication. Self-organizing map is an artificial neural network which helps in iris image recognition. This network has the ability to learn the input features and perform classification. However, from the literature it is observed that the performance of this classifier has scope for refinement to yield better classification. In this paper, heterogeneous methods are adapted to improve the performance of the classifier for iris image recognition. The heterogeneous methods involve the application of Gravity Search Optimization, Teacher Learning Based Optimization, Whale Optimization and Gray Wolf Optimization in the training process of the self-organizing map classifier. This method was tested on iris images from IIT-Delhi database. The results of the experiment show that the proposed method performs better.


Performance comparison of feature extraction methods for iris recognition
J. Winston and D. Hemanth




Moments-Based Feature Vector Extraction for Iris Recognition
J. Jenkin Winston and D. Jude Hemanth
Springer Singapore



A comprehensive review on iris image-based biometric system
J. Jenkin Winston and D. Jude Hemanth
Springer Science and Business Media LLC



Classifiers in IRIS Biometrics for Personal Authentication
S Pradeepa, R Anisha, and Winston J Jenkin
IEEE
Machine learning is that which provides the systems the ability to improve on experience without being programmed. Higher accuracy rate is a challenging problem with Iris biometrics. In this paper the best performance based on the classifiers for iris biometric is identified. The normalized iris images are downloaded from IIT Delhi database. The features are extracted from normalized iris images using the techniques such as histogram and wavelet transform. The extracted features are then classified using Neural Networks and Support Vector Machine. The study shows that support vector machine has far better recognition rate than back propagation neural network. The proposed technique provides accuracy at the rate of 96.7% than the neural network.


Iris Image Error Correction Techniques
Jenkin Winston, Prashanthi, Olive Teresa, Shruti Sekar, and Sarah
IEEE
In today's world, security has gotten paramount. Many biometric methods like facial expression recognition system and Iris recognition system have been developed. Iris biometry helps in identifying an individual in a more intuitive and natural manner. Iris recognition focuses on recognizing the identity of individuals using the textural based characteristics. But, due to various reasons corruption of texture features of iris often occurs during denoising and deblurring. In this paper we propose maltlab algorithms to overcome these defects as well as extract the features to receive a defect less image. To verify the algorithm white noise is added to the iris dataset and the calculations are done as required. This process shows that denoising and deblurring can improve the quality of the iris image evidently.


Iris image recognition using optimized kohonen self organizing neural network
J.J. Winston, D.J. Hemanth, A. Angelopoulou, and E. Kapetanios
Institution of Engineering and Technology
The pursuit to develop an effective people management system has widened over the years to manage the enormous increase in population. Any management system includes identification, verification and recognition stages. Iris recognition has become notable biometrics to support the management system due to its versatility and non-invasive approach. These systems help to identify the individual with the texture information distributed around the iris region. Many classification algorithms are available to help in iris recognition. But those are very sophisticated and require heavy computation. In this paper, an improved Kohonen self-organizing neural network (KSONN) is used to boost the performance of existing KSONN. This improvement is brought by the introduction of optimization technique into the learning phase of the KSONN. The proposed method shows improved accuracy of the recognition. Moreover, it also reduces the iterations required to train the network. From the experimental results, it is observed that the proposed method achieves a maximum accuracy of 98% in 85 iterations.


Pyramid-Based Multi-scale Enhancement Method for Iris Images
J. Jenkin Winston and D. Jude Hemanth
Springer Singapore



Authentication of biometric system using fingerprint recognition with euclidean distance and neural network classifier




Prominence of cooperative communication in 5G cognitive radio systems
G. Shine Let, G. Josemin Bala, J. Jenkin Winston, M. Deepak Raj, and C. Benin Pratap
IEEE
Cognitive Radio is a promising way to overcome the spectrum scarcity for wireless communication and improving the spectral efficiency by using the vacant licensed spectrum band. Cooperative communication is a new communication technique which utilizes the help of neighboring nodes to reduce the bit error rate (BER) in a harmful fading environment. The challenging factor is to combine the cooperative communication in cognitive radio to improve the spectral efficiency and to reduce the BER factor of unlicensed user's communication. In this paper, a comparative study of different communication techniques are done by considering Rayleigh fading channel environment and the advantages of cooperative communication is analyzed. Also, the paper deals with the challenges of integrating cooperative communication in cognitive radio network are discussed.


Novel local binary textural pattern for analysis and classification of mammogram using support vector machine
Narain Ponraj, Jenkin Winston, Poongodi, and Merlin Mercy
IEEE
Breast cancer is one of the most devastating and deadly diseases for women. It is estimated that between one in eight and one in twelve women will develop breast cancer during their lifetime. The most convenient practical method to detect breast cancer is mammography, because it allows the detection of the cancer at its early stages, a crucial issue for a high survival rate. Mammography is the only technique that has demonstrated the ability to detect breast cancer at an early stage and with high sensitivity and specificity. The search for features in this kind of image is complicated by the higher frequency textural variations in image intensity. In this paper, we have proposed few novel local binary textural patterns for classification of mammogram which was found to have consistent accuracy rate.


Improving sensing and throughput of the cognitive radio network
J. Christopher Clement, D. S. Emmanuel, and J. Jenkin Winston
Springer Science and Business Media LLC

RECENT SCHOLAR PUBLICATIONS

Effective Detection of Copy Move Forgery Using Surf
RA Rakhi, AJ Sundararaj, RC Joy, JJ Winston
2023 4th International Conference on Signal Processing and Communication 2023



A miniaturized uniplanar MIMO antenna for n79/n46/millimeter‐wave applications
J Joseph, GS Let, CB Pratap, JJ Winston
International Journal of Communication Systems, e5477 2023



Hybrid deep convolutional neural models for iris image recognition
JJ Winston, DJ Hemanth, A Angelopoulou, E Kapetanios
Multimedia Tools and Applications 81 (7), 9481-9503 2022



Vulnerabilities and Ethical Issues in Machine Learning for Smart City Applications
KM Sagayam, R Jeyasingh, JJ Winston, T Jose
Machine Learning Techniques for Smart City Applications: Trends and 2022



Combination of Thermal and sRGB imaging Techniques for Advanced Surveillance System
KM Sagayam, JJ Winston, MH Abd Wahab, B Bhushan, R Ambar, ...
Annals of Emerging Technologies in Computing (AETiC) 5 (5) 2021



Performance‐enhanced modified self‐organising map for iris data classification
JJ Winston, DJ Hemanth
Expert Systems 38 (1), e12467 2021



Novel Optimization Based Hybrid Self-Organizing Map Classifiers for Iris Image Recognition
JJ Winston, GF Turker, U Kose, DJ Hemanth
International Journal of Computational Intelligence Systems 13 (1), 1048-1058 2020



Performance Comparison of Feature Extraction Methods for Iris Recognition
JJ Winston, DJ Hemanth
Information Technology and Intelligent Transportation Systems 323, 62 2020



Moments-Based Feature Vector Extraction for Iris Recognition
JJ Winston, DJ Hemanth
International Conference on Innovative Computing and Communications 2020



A comprehensive review on iris image-based biometric system
JJ Winston, DJ Hemanth
Soft Computing 23 (19), 9361-9384 2019



Iris Image Error Correction Techniques
J Winston, O Teresa, S Sekar
2019 2nd International Conference on Signal Processing and Communication 2019



Authentication of biometric system using fingerprint recognition with euclidean distance and neural network classifier
KM Sagayam, DN Ponraj, J Winston, JC Yaspy, DE Jeba, A Clara
Int. J. Innov. Technol. Explor. Eng 8 (4), 766-771 2019



Iris Image Recognition using Optimized Kohonen Self Organizing Neural Network
JJ Winston, DJ Hemanth, A Angelopoulou, E Kapetanios
IET Digital Library 2019



Pyramid-Based Multi-scale Enhancement Method for Iris Images
JJ Winston, DJ Hemanth
Recent Trends in Signal and Image Processing, 13-21 2019



Novel local binary textural pattern for analysis and classification of mammogram using support vector machine
N Ponraj, J Winston, M Mercy
2017 International Conference on Signal Processing and Communication (ICSPC 2017



Prominence of cooperative communication in 5G cognitive radio systems
GS Let, GJ Bala, JJ Winston, MD Raj, CB Pratap
2017 International Conference on Circuit, Power and Computing Technologies 2017



Improving Sensing and Throughput of the Cognitive Radio Network
JC Clement, DS Emmanuel, JJ Winston
Circuits, Systems, and Signal Processing 34 (1), 249-267 2015

MOST CITED SCHOLAR PUBLICATIONS

A comprehensive review on iris image-based biometric system
JJ Winston, DJ Hemanth
Soft Computing 23 (19), 9361-9384 2019
Citations: 59



Authentication of biometric system using fingerprint recognition with euclidean distance and neural network classifier
KM Sagayam, DN Ponraj, J Winston, JC Yaspy, DE Jeba, A Clara
Int. J. Innov. Technol. Explor. Eng 8 (4), 766-771 2019
Citations: 34



Hybrid deep convolutional neural models for iris image recognition
JJ Winston, DJ Hemanth, A Angelopoulou, E Kapetanios
Multimedia Tools and Applications 81 (7), 9481-9503 2022
Citations: 21



Prominence of cooperative communication in 5G cognitive radio systems
GS Let, GJ Bala, JJ Winston, MD Raj, CB Pratap
2017 International Conference on Circuit, Power and Computing Technologies 2017
Citations: 12



Improving Sensing and Throughput of the Cognitive Radio Network
JC Clement, DS Emmanuel, JJ Winston
Circuits, Systems, and Signal Processing 34 (1), 249-267 2015
Citations: 12



Performance‐enhanced modified self‐organising map for iris data classification
JJ Winston, DJ Hemanth
Expert Systems 38 (1), e12467 2021
Citations: 7



Novel Optimization Based Hybrid Self-Organizing Map Classifiers for Iris Image Recognition
JJ Winston, GF Turker, U Kose, DJ Hemanth
International Journal of Computational Intelligence Systems 13 (1), 1048-1058 2020
Citations: 7



Moments-Based Feature Vector Extraction for Iris Recognition
JJ Winston, DJ Hemanth
International Conference on Innovative Computing and Communications 2020
Citations: 6



Novel local binary textural pattern for analysis and classification of mammogram using support vector machine
N Ponraj, J Winston, M Mercy
2017 International Conference on Signal Processing and Communication (ICSPC 2017
Citations: 4



A miniaturized uniplanar MIMO antenna for n79/n46/millimeter‐wave applications
J Joseph, GS Let, CB Pratap, JJ Winston
International Journal of Communication Systems, e5477 2023
Citations: 3



Performance Comparison of Feature Extraction Methods for Iris Recognition
JJ Winston, DJ Hemanth
Information Technology and Intelligent Transportation Systems 323, 62 2020
Citations: 3



Iris Image Recognition using Optimized Kohonen Self Organizing Neural Network
JJ Winston, DJ Hemanth, A Angelopoulou, E Kapetanios
IET Digital Library 2019
Citations: 2