Sourav Dey Roy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sourav Dey Roy has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Mrinal Kanti Bhowmik
Department of Computer Science and Engineering, Tripura University (A Central University), Suryamaninagar, India
11 shared publications - Niharika Nath
New York Institute of Technology
3 shared publications - Anindita Mohanta
Tripura University (A Central University)
2 shared publications - Dipak Hrishi Das
Department of Information Technology, Government Degree College, Santirbazar, India
2 shared publications - Priya Saha
Department of Cyber Security and Digital Forensics, National Forensic Sciences University (Tripura Campus), Agartala, India
2 shared publications - Abhijit Datta
Department of Pathology, Agartala Government Medical College (AGMC), Tripura, India
1 shared publication
Latest Publications
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (9) , 2354-2383
A Comprehensive Survey on Diagnostic Microscopic Imaging Modalities, Challenges, Taxonomy, and Future Directions for Cervical Abnormality Detection and Grading
Cancer is one of the most severe diseases, affecting the lives of many people in the modern world. Among the various types of cancer, cervical cancer is one of the most frequently occurring cancers in the female population. In most cases, doctors and practitioners can typically only identify cervical cancer in its latter stages. Planning cancer therapy and increasing patient survival rates become very difficult as the disease progresses. As a result, diagnosing cervical cancer in its initial stages has become imperative to arrange proper therapy and surgery. In this paper, we present a survey of automatic computerized methods for diagnosing cervical abnormalities based on microscopic imaging modalities. The present survey was conducted by defining a novel taxonomy of the surveyed techniques based on the approaches they used. We also discuss the challenges and sub-challenges associated with an automatic cervical cancer diagnosis based on microscopic imaging modalities. Additionally, surveys on various public and private datasets used by the research community for developing new methods are presented. In this paper, the performances of published papers are compared. The paper concludes by suggesting possible research directions in these fields.
- 13 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (9) , 2354-2383
A Comprehensive Survey on Diagnostic Microscopic Imaging Modalities, Challenges, Taxonomy, and Future Directions for Cervical Abnormality Detection and Grading
Cancer is one of the most severe diseases, affecting the lives of many people in the modern world. Among the various types of cancer, cervical cancer is one of the most frequently occurring cancers in the female population. In most cases, doctors and practitioners can typically only identify cervical cancer in its latter stages. Planning cancer therapy and increasing patient survival rates become very difficult as the disease progresses. As a result, diagnosing cervical cancer in its initial stages has become imperative to arrange proper therapy and surgery. In this paper, we present a survey of automatic computerized methods for diagnosing cervical abnormalities based on microscopic imaging modalities. The present survey was conducted by defining a novel taxonomy of the surveyed techniques based on the approaches they used. We also discuss the challenges and sub-challenges associated with an automatic cervical cancer diagnosis based on microscopic imaging modalities. Additionally, surveys on various public and private datasets used by the research community for developing new methods are presented. In this paper, the performances of published papers are compared. The paper concludes by suggesting possible research directions in these fields.
- 27 February 2025
- Published by Springer Nature
- p. 129-143
Multi-class Histology Image Analysis Using Handcrafted Texture and Colour Features for Breast Abnormality Classification
- 27 February 2025
- Published by Springer Nature
- p. 129-143
Multi-class Histology Image Analysis Using Handcrafted Texture and Colour Features for Breast Abnormality Classification
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 2423-2444
An Attention Network for Detection of Spliced Video Objects Inspired by Manipulated Visual Social Media Privacy Sensitive Issues Using NV2CIR Dataset
Even though forgery detection is a well matured topic, reporting on the same for detection of forgery in night time outdoor scenes is not explored to date. Despite the lack of appropriate benchmark video datasets for forgery detection at night time using infrared (IR) video modality, we designed a novel ground truth annotated forged video dataset named as “NV2CIR (Night Vision Video Forensic Challenges based IR Forged Dataset)” in real-world night time situations. The dataset contains various 310 infrared imaging based forged videos (i.e., object based forgery, interframe forgery, and intraframe forgery) and their corresponding 310 authentic videos. The article also proposed a novel framework named as “AFOD-Net (attention guided fake object detection network)” for localization of spliced objects in night vision outdoor scenarios. The proposed network employs a long short term memory (LSTM) module and our proposed spliced object attention module (SOA) so as to precisely localize the spatio-temporal spliced regions. Experimental results show that AFOD-Net significantly improves the performance for localizing the spliced objects on our designed spliced video dataset with mean average precision (mAP) of 85.16%.
- 13 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 12 (5) , 2423-2444
An Attention Network for Detection of Spliced Video Objects Inspired by Manipulated Visual Social Media Privacy Sensitive Issues Using NV2CIR Dataset
Even though forgery detection is a well matured topic, reporting on the same for detection of forgery in night time outdoor scenes is not explored to date. Despite the lack of appropriate benchmark video datasets for forgery detection at night time using infrared (IR) video modality, we designed a novel ground truth annotated forged video dataset named as “NV2CIR (Night Vision Video Forensic Challenges based IR Forged Dataset)” in real-world night time situations. The dataset contains various 310 infrared imaging based forged videos (i.e., object based forgery, interframe forgery, and intraframe forgery) and their corresponding 310 authentic videos. The article also proposed a novel framework named as “AFOD-Net (attention guided fake object detection network)” for localization of spliced objects in night vision outdoor scenarios. The proposed network employs a long short term memory (LSTM) module and our proposed spliced object attention module (SOA) so as to precisely localize the spatio-temporal spliced regions. Experimental results show that AFOD-Net significantly improves the performance for localizing the spliced objects on our designed spliced video dataset with mean average precision (mAP) of 85.16%.
- 23 July 2024
- Published by Springer Nature in Innovations in Systems and Software Engineering
- Vol. 21 (4) , 1123-1131
A novel self-attention guided deep neural network for bruise segmentation using infrared imaging
- 23 July 2024
- Published by Springer Nature in Innovations in Systems and Software Engineering
- Vol. 21 (4) , 1123-1131
A novel self-attention guided deep neural network for bruise segmentation using infrared imaging
- 5 July 2024
- Published by Elsevier in Journal of Thermal Biology
- Vol. 123, 103915
Infrared thermogram image guided discontinuous appearances of hyaluronic acid for classification of arthritic knee joints
- 5 July 2024
- Published by Elsevier in Journal of Thermal Biology
- Vol. 123, 103915
Infrared thermogram image guided discontinuous appearances of hyaluronic acid for classification of arthritic knee joints
- 16 April 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (9) , 6025-6071
A comprehensive review on deep cardiovascular disease detection approaches: its datasets, image modalities and methods
- 16 April 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (9) , 6025-6071
A comprehensive review on deep cardiovascular disease detection approaches: its datasets, image modalities and methods
- 5 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 2 (1) , 105-124
TU-IR Apple Image Dataset: Benchmarking, Challenges, and Asymmetric Characterization for Bruise Detection in Application of Automatic Harvesting
With the blooming interest in computer vision-based technologies for future automation of food producers, there is a need for incorporating an automatic bruise detection module in robotic apple harvesting because of decreasing accessibility and growing labor costs. Although numerous studies have been published for automatic quality inspection of fruit and other agricultural products, there is a lack of publicly available image-based datasets for quality inspection/automatic detection of bruises. Toward the aim of developing a bruise detection system for apple harvesting, especially at night time, this article describes the designing issues (i.e., protocol) and creation of a new infrared imaging-based dataset titled “TU-IR Apple Image Dataset,” which contains 1375 infrared images of apples defining four major categories of bruises (i.e., fresh, slight, moderate, and severe). Along with the infrared images, ground truths (in the form of binary masks) and measurements of suspicious bruised regions are defined. This study also investigates the efficiency of infrared imaging technology for automatic bruise detection in apples by performing an analysis of temperature-based, intensity-based, texture-based, shape-based, and deep convolutional neural network-based features. The classification performance was evaluated using eight different feature sets. Based on the experimental results, considering the most outer-performed classifier, deep convolutional neural networks as a fixed feature extraction method were found to provide the highest prediction performance for discriminating between fresh and three categories of bruises in apples with an average accuracy, specificity, and sensitivity of 93.87%, 80.57%, and 92.02%, respectively.
- 5 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on AgriFood Electronics
- Vol. 2 (1) , 105-124
TU-IR Apple Image Dataset: Benchmarking, Challenges, and Asymmetric Characterization for Bruise Detection in Application of Automatic Harvesting
With the blooming interest in computer vision-based technologies for future automation of food producers, there is a need for incorporating an automatic bruise detection module in robotic apple harvesting because of decreasing accessibility and growing labor costs. Although numerous studies have been published for automatic quality inspection of fruit and other agricultural products, there is a lack of publicly available image-based datasets for quality inspection/automatic detection of bruises. Toward the aim of developing a bruise detection system for apple harvesting, especially at night time, this article describes the designing issues (i.e., protocol) and creation of a new infrared imaging-based dataset titled “TU-IR Apple Image Dataset,” which contains 1375 infrared images of apples defining four major categories of bruises (i.e., fresh, slight, moderate, and severe). Along with the infrared images, ground truths (in the form of binary masks) and measurements of suspicious bruised regions are defined. This study also investigates the efficiency of infrared imaging technology for automatic bruise detection in apples by performing an analysis of temperature-based, intensity-based, texture-based, shape-based, and deep convolutional neural network-based features. The classification performance was evaluated using eight different feature sets. Based on the experimental results, considering the most outer-performed classifier, deep convolutional neural networks as a fixed feature extraction method were found to provide the highest prediction performance for discriminating between fresh and three categories of bruises in apples with an average accuracy, specificity, and sensitivity of 93.87%, 80.57%, and 92.02%, respectively.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-20
Understanding Adversarial Atmospheric Features Interpretation, Analysis, and Standardization for Tackling the Computer Vision Problems in Videos
In real-world situations, the performance of vision based systems in indoor environments has been observed to provide noticeable results. However, in the case of the outdoor environment, the proper functioning of vision based systems is often disrupted due to the occurrence of atmospheric/ weather effects. To ensure the functional operation of all vision-based devices in any weather condition, a reliable classification/recognition system is needed to identify the weather pertinent to the scenes for effective removal. Consequently, a trustworthy classification/ recognition system is required to recognize the weather pertinent to the outdoor scenes for its effective removal to guarantee the efficient functioning of all vision based systems in any weather situation. For this, the present work investigated and analysed the performance of conventional handcrafted features extracted from outdoor scenes to solve the problem of atmospheric/ weather classification tasks in real-world outdoor scenes. Recently, convolutional neural network (CNNs) based architectures have been used by research communities for solving many vision based problems. Motivated by the enormous success of CNNs, in the present scope of this article, the perception capability of deep CNN features is also investigated for effective analysis and discrimination of atmospheric/ weather degraded scenes. To achieve the precise necessities of the objectives, several experiments were conducted. The analysis and experiments were carried out using the created Extended Tripura University Video Dataset (E-TUVD), which consists of a diverse set of atmospheric/ weather degraded outdoor scenes. The experiment results reveal that effectively selecting the discriminative features, thereby describing the weather properties, can improve classification accuracy and provide an accurate weather type classification using machine learning classifiers.
- 25 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-20
Understanding Adversarial Atmospheric Features Interpretation, Analysis, and Standardization for Tackling the Computer Vision Problems in Videos
In real-world situations, the performance of vision based systems in indoor environments has been observed to provide noticeable results. However, in the case of the outdoor environment, the proper functioning of vision based systems is often disrupted due to the occurrence of atmospheric/ weather effects. To ensure the functional operation of all vision-based devices in any weather condition, a reliable classification/recognition system is needed to identify the weather pertinent to the scenes for effective removal. Consequently, a trustworthy classification/ recognition system is required to recognize the weather pertinent to the outdoor scenes for its effective removal to guarantee the efficient functioning of all vision based systems in any weather situation. For this, the present work investigated and analysed the performance of conventional handcrafted features extracted from outdoor scenes to solve the problem of atmospheric/ weather classification tasks in real-world outdoor scenes. Recently, convolutional neural network (CNNs) based architectures have been used by research communities for solving many vision based problems. Motivated by the enormous success of CNNs, in the present scope of this article, the perception capability of deep CNN features is also investigated for effective analysis and discrimination of atmospheric/ weather degraded scenes. To achieve the precise necessities of the objectives, several experiments were conducted. The analysis and experiments were carried out using the created Extended Tripura University Video Dataset (E-TUVD), which consists of a diverse set of atmospheric/ weather degraded outdoor scenes. The experiment results reveal that effectively selecting the discriminative features, thereby describing the weather properties, can improve classification accuracy and provide an accurate weather type classification using machine learning classifiers.
- 4 December 2023
- Published by Springer Nature
- p. 407-417
Domain Adapted Few-Shot Learning for Breast Histopathological Image Classification
- 4 December 2023
- Published by Springer Nature
- p. 407-417
Domain Adapted Few-Shot Learning for Breast Histopathological Image Classification