Swati D. Shirke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Swati D. Shirke has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
C. Rajabhushnam
4 shared publicationsC. Rajabhushanam
2 shared publications- Alice Hepzibah Albert
Department of Electrical and Electronics Engineering Sri Sairam Institute of Technology Chennai Tamilnadu India
1 shared publication Amol Bhand
Savitrybai Phule Pune University
1 shared publication- Anuj Kumar Singh
Galgotias University
1 shared publication C. RajaBhushnam
Bharath University Chennai
1 shared publication
Latest Publications
- 18 June 2025
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 38 (01)
NAS-QDCNN: NEURON ATTENTION STAGE-BY-STAGE QUANTUM DILATED CONVOLUTIONAL NEURAL NETWORK FOR IRIS RECOGNITION AT A DISTANCE
Biometric identification has become a vital approach for ensuring information security. Identifying persons on the basis of their biometric features is a major aspect of identification technology. Iris recognition (IR) is useful for recognizing persons and several iris recognition at-a-distance (IAAD) systems have been introduced for extracting iris features and improving iris image quality in biometric systems. Moreover, despite higher quality images, accuracy is the major challenging problem. To bridge this gap, neuron attention stage-by-stage quantum dilated convolutional neural network (NAS-QDCNN) is developed here for IAAD using iris images. Then, iris images are preprocessed employing the Kalman filtering and region of interest (ROI) extraction technique. After preprocessing, the segmentation process is conducted utilizing the Daugman rubber sheet model. Then, the feature extraction process is conducted on segmented iris images by extracting features, such as fast retina keypoint (FREAK) and gray-level co-occurrence matrix (GLCM). Based on the extracted features, IR is performed at a distance using the NAS-QDCNN method, which is the combination of neuron attention stage-by-stage net (NASNet) and quantum dilated convolutional neural network (QDCNN). It is noticed that NAS-QDCNN has gained a high accuracy of 96.838%, and minimum false rejection rate (FRR) of 0.311% and a false acceptance range (FAR) of 0.453%. The NAS-QDCNN method effectively enhances IR making it a promising solution for biometric identification systems.
- 18 June 2025
- Published by National Taiwan University in Biomedical Engineering: Applications, Basis and Communications
- Vol. 38 (01)
NAS-QDCNN: NEURON ATTENTION STAGE-BY-STAGE QUANTUM DILATED CONVOLUTIONAL NEURAL NETWORK FOR IRIS RECOGNITION AT A DISTANCE
Biometric identification has become a vital approach for ensuring information security. Identifying persons on the basis of their biometric features is a major aspect of identification technology. Iris recognition (IR) is useful for recognizing persons and several iris recognition at-a-distance (IAAD) systems have been introduced for extracting iris features and improving iris image quality in biometric systems. Moreover, despite higher quality images, accuracy is the major challenging problem. To bridge this gap, neuron attention stage-by-stage quantum dilated convolutional neural network (NAS-QDCNN) is developed here for IAAD using iris images. Then, iris images are preprocessed employing the Kalman filtering and region of interest (ROI) extraction technique. After preprocessing, the segmentation process is conducted utilizing the Daugman rubber sheet model. Then, the feature extraction process is conducted on segmented iris images by extracting features, such as fast retina keypoint (FREAK) and gray-level co-occurrence matrix (GLCM). Based on the extracted features, IR is performed at a distance using the NAS-QDCNN method, which is the combination of neuron attention stage-by-stage net (NASNet) and quantum dilated convolutional neural network (QDCNN). It is noticed that NAS-QDCNN has gained a high accuracy of 96.838%, and minimum false rejection rate (FRR) of 0.311% and a false acceptance range (FAR) of 0.453%. The NAS-QDCNN method effectively enhances IR making it a promising solution for biometric identification systems.
- Open Access
- 5 June 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- Vol. 11 (8s) , 375-380
Machine Learning-Based Credit Card Fraud Detection: A Comparative Study Using Logistic Regression, SVM, and KNN
The increasing threat of credit card fraud in the digital age necessitates robust and intelligent detection systems. This study investigates the application of machine learning algorithms—Logistic Regression, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—to identify fraudulent credit card transactions. Using a real-world dataset, the research addresses issues of class imbalance with the SMOTE technique and develops models capable of classifying transactions with high precision and recall. A web-based fraud detection system is also designed to visualize and evaluate model performance. The results highlight the effectiveness of machine learning in real-time fraud detection and present a scalable system framework suitable for deployment in modern financial infrastructures.
- 5 June 2025
- Published by Academic Science Publications and Distributions in International Journal of Environmental Sciences
- Vol. 11 (8s) , 375-380
Open AccessMachine Learning-Based Credit Card Fraud Detection: A Comparative Study Using Logistic Regression, SVM, and KNN
The increasing threat of credit card fraud in the digital age necessitates robust and intelligent detection systems. This study investigates the application of machine learning algorithms—Logistic Regression, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—to identify fraudulent credit card transactions. Using a real-world dataset, the research addresses issues of class imbalance with the SMOTE technique and develops models capable of classifying transactions with high precision and recall. A web-based fraud detection system is also designed to visualize and evaluate model performance. The results highlight the effectiveness of machine learning in real-time fraud detection and present a scalable system framework suitable for deployment in modern financial infrastructures.
- 8 November 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045225
A novel approach to iris recognition at-a-distance: leveraging BW-CNN framework
This paper introduces a novel iris recognition framework by integrating the Black Widow Optimization (BWO) algorithm with Convolutional Neural Networks (CNNs), forming the Black Widow-CNN (BW-CNN) framework. The necessity of this work stems from the increasing demand for secure and reliable biometric systems, particularly in iris recognition, which has become a critical tool in sectors such as national security, financial transactions, and contactless access controls. Traditional iris recognition systems face significant limitations under varying environmental conditions and subject distances, often compromising accuracy. The proposed BW-CNN framework is necessary as it addresses these challenges by offering a robust solution capable of precise iris detection even at a distance and in challenging real-world conditions. This approach enhances feature extraction and classification accuracy and streamlines the recognition process. The experimental results, evaluated across multiple datasets, demonstrate the superior performance of the BW-CNN framework over existing methods, showcasing its potential for deployment in high-security and real-time applications.
- 8 November 2024
- Published by IOP Publishing in Engineering Research Express
- Vol. 6 (4) , 045225
A novel approach to iris recognition at-a-distance: leveraging BW-CNN framework
This paper introduces a novel iris recognition framework by integrating the Black Widow Optimization (BWO) algorithm with Convolutional Neural Networks (CNNs), forming the Black Widow-CNN (BW-CNN) framework. The necessity of this work stems from the increasing demand for secure and reliable biometric systems, particularly in iris recognition, which has become a critical tool in sectors such as national security, financial transactions, and contactless access controls. Traditional iris recognition systems face significant limitations under varying environmental conditions and subject distances, often compromising accuracy. The proposed BW-CNN framework is necessary as it addresses these challenges by offering a robust solution capable of precise iris detection even at a distance and in challenging real-world conditions. This approach enhances feature extraction and classification accuracy and streamlines the recognition process. The experimental results, evaluated across multiple datasets, demonstrate the superior performance of the BW-CNN framework over existing methods, showcasing its potential for deployment in high-security and real-time applications.
- 17 October 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Wavelets, Multiresolution and Information Processing
- Vol. 22 (02)
Effective face recognition with hybrid distance-key frame selection using TBO-ensemble model
The enormous amount of data contained in the video image has grown rapidly along with surveillance, greatly outpacing the capacity of human resources to handle it effectively. Smart surveillance retrieval is an essential component of any modern video surveillance system, considerably boosting the effectiveness, precision, and interoperability of the system. The use of face recognition and other cutting-edge technology in the security surveillance system is rapidly rising. Therefore, in this article, the distributed deep convolutional neural network (DCNN) and distributed deep BiLSTM is proposed to efficiently detect the face from the video. One of the major contributions involved in this research relies on the key frame selection, where four unique distance measurement techniques are fused, and is named hybrid distance- key frame selection. The Tri birds optimization (TBO) technique selects the best solution from a large number of solutions for the ensemble model classifier engaged in face recognition. The ensemble model classifier incorporates various hyper-parameters that are optimally trained. Multiple test videos with 401 and 802 test videos are used as the input for the TBO-ensemble model that attains 97% accuracy, 98.33% precision, recall, and f-measure for epoch 50 and the 500 number of retrievals, respectively.
- 17 October 2023
- Published by World Scientific Pub Co Pte Ltd in International Journal of Wavelets, Multiresolution and Information Processing
- Vol. 22 (02)
Effective face recognition with hybrid distance-key frame selection using TBO-ensemble model
The enormous amount of data contained in the video image has grown rapidly along with surveillance, greatly outpacing the capacity of human resources to handle it effectively. Smart surveillance retrieval is an essential component of any modern video surveillance system, considerably boosting the effectiveness, precision, and interoperability of the system. The use of face recognition and other cutting-edge technology in the security surveillance system is rapidly rising. Therefore, in this article, the distributed deep convolutional neural network (DCNN) and distributed deep BiLSTM is proposed to efficiently detect the face from the video. One of the major contributions involved in this research relies on the key frame selection, where four unique distance measurement techniques are fused, and is named hybrid distance- key frame selection. The Tri birds optimization (TBO) technique selects the best solution from a large number of solutions for the ensemble model classifier engaged in face recognition. The ensemble model classifier incorporates various hyper-parameters that are optimally trained. Multiple test videos with 401 and 802 test videos are used as the input for the TBO-ensemble model that attains 97% accuracy, 98.33% precision, recall, and f-measure for epoch 50 and the 500 number of retrievals, respectively.
- 30 October 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 9 (1) , 5200-5204
Structure of Iris Recognition technique
In many iris recognizable proof frameworks, the total image obtains requirements are understood. These imperatives incorporate close infrared (NIR) enlightenment to release the co-events of surface measures in the mirror plane of human iris, just as closeness in the output lines of a device. In ongoing advances to various light developments presented in images caught in the earth. This condition incorporates an obvious wavelength (VW) light source a good way off over the nearby good ways from the catching device. For precise Iris recognizable proof a ways off, eye images require improvement of successful systems, whereas the light source is situating good ways off after the planar perspective on the iris. Adequately acting a highpoint abstraction system aimed at Close Infrared too Obvious wavelength images, the images are composed unrestrained point. The recognizable proof of iris exactness on the freely accessible database remained estimated here uses Hough transform algorithm to caught utilizing straight extending and turn for standardization. for utilizing towards channel also differentiation stretches the iris areas from multispectral iris images. An essential motivation behind this examination is to encompass a structure and actualize IRIS-recognition a good ways off (IAAD) by embracing a recurrence then Hough Transform change intended for exact element choice [1][2]. Here proposed strategy is depicted as pursues: At first, the information iris image will be exposed in the direction of pre-handling though at the same time separating highpoints with contrasts from neighborhood extrema also highest conditions. [3][4].
- 30 October 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 9 (1) , 5200-5204
Structure of Iris Recognition technique
In many iris recognizable proof frameworks, the total image obtains requirements are understood. These imperatives incorporate close infrared (NIR) enlightenment to release the co-events of surface measures in the mirror plane of human iris, just as closeness in the output lines of a device. In ongoing advances to various light developments presented in images caught in the earth. This condition incorporates an obvious wavelength (VW) light source a good way off over the nearby good ways from the catching device. For precise Iris recognizable proof a ways off, eye images require improvement of successful systems, whereas the light source is situating good ways off after the planar perspective on the iris. Adequately acting a highpoint abstraction system aimed at Close Infrared too Obvious wavelength images, the images are composed unrestrained point. The recognizable proof of iris exactness on the freely accessible database remained estimated here uses Hough transform algorithm to caught utilizing straight extending and turn for standardization. for utilizing towards channel also differentiation stretches the iris areas from multispectral iris images. An essential motivation behind this examination is to encompass a structure and actualize IRIS-recognition a good ways off (IAAD) by embracing a recurrence then Hough Transform change intended for exact element choice [1][2]. Here proposed strategy is depicted as pursues: At first, the information iris image will be exposed in the direction of pre-handling though at the same time separating highpoints with contrasts from neighborhood extrema also highest conditions. [3][4].
- 30 October 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Innovative Technology and Exploring Engineering
- Vol. 8 (12) , 4540-4552
Iris Recognition at-a-Distance by Means of Chronological MBO-Based DBN
Now a days, Iris recognition is wieldy used for the identification of person. The superior bit of 1 countries exploits biometric system for safety reason with the conclusion goal that in runway boarding, custom freedom, gathering passage, etc. The Iris detection at-a-Distance (IAAD) framework is generally used to identify the person in most of the applications. In this system, different features of iris image are extracted in addition enhances the superiority of iris image. Over the span of the most recent ages there consume raised various structures to design and finish iris affirmation systems which works at longer separation going from one meter to sixty meter. Because of such long scope of iris detection schemes in addition iris attainment scheme provides for the best applications to the client. Therefore, It is necessary to design an effective algorithm for IAAD is necessary. In this article, an actual method for iris recognition is presents. A Chronological Monarch Butterfly Optimization -based Deep Belief Network (Chronological MBO-based DBN) technique is anticipated for iris detection.This technique algorithm is the combination of Chronological theory with the Monarch Butterfly Optimization. It is utilized to mastermind the sequential presumption of an iris picture. Additionally, the Hough Transform calculation is utilized for discovery of iris circle and edge. To enhance the accuracy of anticipated iris recognition system ScatT-Loop descriptor and the Local Gradient Pattern (LGP) are fed to the Chronological MBO-based DBN algorithm and these are castoff to abstract the dissimilar features of an iris picture. The dataset used for these tactices are UBIRIS.v1 For the normalization and segmentation of an iris image is done by by means of Dougman's rubber sheet model. This system is established on MATLAB for executing the Hough transform procedures also for reading the iris images. The simulation results shows that this system successfully recognize the iris at a distance 4 to 8 meter. Different performance parameters like as FAR accuracy, too FRR shows better results in this anticipated work.
- 30 October 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Innovative Technology and Exploring Engineering
- Vol. 8 (12) , 4540-4552
Iris Recognition at-a-Distance by Means of Chronological MBO-Based DBN
Now a days, Iris recognition is wieldy used for the identification of person. The superior bit of 1 countries exploits biometric system for safety reason with the conclusion goal that in runway boarding, custom freedom, gathering passage, etc. The Iris detection at-a-Distance (IAAD) framework is generally used to identify the person in most of the applications. In this system, different features of iris image are extracted in addition enhances the superiority of iris image. Over the span of the most recent ages there consume raised various structures to design and finish iris affirmation systems which works at longer separation going from one meter to sixty meter. Because of such long scope of iris detection schemes in addition iris attainment scheme provides for the best applications to the client. Therefore, It is necessary to design an effective algorithm for IAAD is necessary. In this article, an actual method for iris recognition is presents. A Chronological Monarch Butterfly Optimization -based Deep Belief Network (Chronological MBO-based DBN) technique is anticipated for iris detection.This technique algorithm is the combination of Chronological theory with the Monarch Butterfly Optimization. It is utilized to mastermind the sequential presumption of an iris picture. Additionally, the Hough Transform calculation is utilized for discovery of iris circle and edge. To enhance the accuracy of anticipated iris recognition system ScatT-Loop descriptor and the Local Gradient Pattern (LGP) are fed to the Chronological MBO-based DBN algorithm and these are castoff to abstract the dissimilar features of an iris picture. The dataset used for these tactices are UBIRIS.v1 For the normalization and segmentation of an iris image is done by by means of Dougman's rubber sheet model. This system is established on MATLAB for executing the Hough transform procedures also for reading the iris images. The simulation results shows that this system successfully recognize the iris at a distance 4 to 8 meter. Different performance parameters like as FAR accuracy, too FRR shows better results in this anticipated work.
- 14 September 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 8 (5s3) , 539-549
Biometric Private Iris Recognition From An Image at Long Distance: A survey
The specially finished annular element of the person eye which is remotely visible is - iris. This iris recognition is useful to identify the individual. In number of applications the iris recognition system is used. Most of the countries uses biometric system for security purpose such that in airfield boarding, custom clearance, congregation entrance and so on. The Indian government also uses biometric system for identification of citizen in different applications like as in rashan shop, Aadhar project, in different government exam forms and registration dept. etc. The customary iris recognition systems develop near infrared (NIR) sensors to obtain pictures of the iris. But in this method the iris can acquire distance less than 1 meter. In the course of the last several years, there have been different designs to plan and complete iris acknowledgment frameworks which operates at longer distance ranging from 1 meter to 60 meter. Therefore, due to such long range of iris recognition systems and iris acquisition system gives to the best applications to the client. In this paper, an effective technique for iris recognition is present to identify the individual. It uses iris-recognition-at-a-distance (IAAD) system and state-of-the-art design methods to audits the iris recognition system. The primary point of this article is analyzing the criticalness and employments of IAAD systems with respect to human recognition, the review of existing IAAD structures, comparison of different method which are already implemented in literature and improvement of IAAD accuracy along with iris.
- 14 September 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 8 (5s3) , 539-549
Biometric Private Iris Recognition From An Image at Long Distance: A survey
The specially finished annular element of the person eye which is remotely visible is - iris. This iris recognition is useful to identify the individual. In number of applications the iris recognition system is used. Most of the countries uses biometric system for security purpose such that in airfield boarding, custom clearance, congregation entrance and so on. The Indian government also uses biometric system for identification of citizen in different applications like as in rashan shop, Aadhar project, in different government exam forms and registration dept. etc. The customary iris recognition systems develop near infrared (NIR) sensors to obtain pictures of the iris. But in this method the iris can acquire distance less than 1 meter. In the course of the last several years, there have been different designs to plan and complete iris acknowledgment frameworks which operates at longer distance ranging from 1 meter to 60 meter. Therefore, due to such long range of iris recognition systems and iris acquisition system gives to the best applications to the client. In this paper, an effective technique for iris recognition is present to identify the individual. It uses iris-recognition-at-a-distance (IAAD) system and state-of-the-art design methods to audits the iris recognition system. The primary point of this article is analyzing the criticalness and employments of IAAD systems with respect to human recognition, the review of existing IAAD structures, comparison of different method which are already implemented in literature and improvement of IAAD accuracy along with iris.
- Open Access
- 14 September 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 8 (5s3) , 524-527
Iris Recognition from an Image at Lengthy Distance by using Deep Belief Neural Network (DBN)
Now a days, biometric is a one of the best method which is used for the detection of person is iris recognition. A large portion of different frameworks are equally introduces for individual ID like as distinguishing proof cards or tokens, mystery codes, passwords, and so on. Yet, the issues of these sort of frameworks are, the mystery codes and passwords can be split, the recognizable proof cards can be harmed. Subsequently the successful strategy for the individual recognizable proof is vital. Iris gives the unmistakable data about an individual. Iris recognition is the process of identifying persons automatically using their iris. Iris provides the distinctive information about a person. This paper exhibits the deep learning-based methodology for the iris acknowledgment. Firstly, the picture is pre-handled to get the precise area of the iris. From that point onward, iris locale is extricated utilizing Hough Transform, which is pursued with the division and standardization of the iris area utilizing the Daugman's Rubber sheet model. When the division is played out, the features are separated by utilizing the Local Gradient Pattern (LGP) and ScaT-LOOP that is the mixture of Scattering transforms (ST), Tetrolet transforms (TT), and Local Optimal Oriented Pattern (LOOP) descriptors. At last, steepest slope based Deep Belief Neural Network (DBN) is used for the iris acknowledgment. The exhibition of iris acknowledgment utilizing the DBN classifier is assessed regarding precision, False Rejection Rate (FRR) and False Acceptance Rate (FAR). The proposed iris acknowledgment strategy accomplishes the most extreme precision of 97.96%, negligible FAR of 0.493%, and insignificant FRR of 0.48% that shows its predominance.
- 14 September 2019
- Published by Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication (BEIESP) in International Journal of Engineering and Advanced Technology
- Vol. 8 (5s3) , 524-527
Open AccessIris Recognition from an Image at Lengthy Distance by using Deep Belief Neural Network (DBN)
Now a days, biometric is a one of the best method which is used for the detection of person is iris recognition. A large portion of different frameworks are equally introduces for individual ID like as distinguishing proof cards or tokens, mystery codes, passwords, and so on. Yet, the issues of these sort of frameworks are, the mystery codes and passwords can be split, the recognizable proof cards can be harmed. Subsequently the successful strategy for the individual recognizable proof is vital. Iris gives the unmistakable data about an individual. Iris recognition is the process of identifying persons automatically using their iris. Iris provides the distinctive information about a person. This paper exhibits the deep learning-based methodology for the iris acknowledgment. Firstly, the picture is pre-handled to get the precise area of the iris. From that point onward, iris locale is extricated utilizing Hough Transform, which is pursued with the division and standardization of the iris area utilizing the Daugman's Rubber sheet model. When the division is played out, the features are separated by utilizing the Local Gradient Pattern (LGP) and ScaT-LOOP that is the mixture of Scattering transforms (ST), Tetrolet transforms (TT), and Local Optimal Oriented Pattern (LOOP) descriptors. At last, steepest slope based Deep Belief Neural Network (DBN) is used for the iris acknowledgment. The exhibition of iris acknowledgment utilizing the DBN classifier is assessed regarding precision, False Rejection Rate (FRR) and False Acceptance Rate (FAR). The proposed iris acknowledgment strategy accomplishes the most extreme precision of 97.96%, negligible FAR of 0.493%, and insignificant FRR of 0.48% that shows its predominance.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 560-565
Biometric Personal Iris Recognition from an Image at Long Distance
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 560-565
Biometric Personal Iris Recognition from an Image at Long Distance