Gopa Bhaumik

@nitsikkim.ac.in

Assistant Professor, Computer Science and Engineering
NIT Sikkim



              

https://researchid.co/g.bhaumik

RESEARCH INTERESTS

Computer Vision, Image Processing, Deep Learning, Machine Learning

16

Scopus Publications

131

Scholar Citations

6

Scholar h-index

3

Scholar i10-index

Scopus Publications


  • SpAtNet: a spatial feature attention network for hand gesture recognition
    Gopa Bhaumik and Mahesh Chandra Govil
    Springer Science and Business Media LLC

  • Triple Stack Deep Variational Autoencoder For Improved Hand Gesture Recognition
    Arti Bahuguna, Gopa Bhaumik, and Mahesh Chandra Govil
    IEEE
    This paper proposes a novel approach for hand gesture recognition using a triple-stack deep variational autoencoder. By employing a VAE framework, we facilitate both efficient representation learning and the generation of meaningful latent spaces for gesture recognition and classification. This is an extension of the traditional VAE architecture that incorporates three layers of encoding and decoding with a spatial deep neural network. In a regular VAE, there is typically only one layer for both the encoder and decoder. By stacking three layers in both the encoder and decoder, a triple-stack deep VAE can learn more complex hierarchical representations of the input data. Each layer in the encoder extracts increasingly abstract features from the input, while each layer in the decoder reconstructs the input from these abstract representations. The performance of the proposed model is evaluated in terms of accuracy, precision, recall, and F1-score on six benchmark datasets: ASL Static, Massey University Dataset (MUGD), ASL Digit, NUS-2, Bengali Sign Language (BSL), and Hagrid-14 (HG-14) datasets. The results of the experiment show that the proposed 3S-DVE achieves an accuracy of ${7 6 \\%}$ (MUGD Set 1), ${8 0 \\%}$ (MUGD Set 2), ${9 7 \\%}$ (MUGD Set 3), 96% (MUGD Set 4), 86% (MUGD Set 5), ${9 7 \\%}$ (ASL Digit), ${6 2 \\%}$ (ASL Static), ${7 4 \\%}$ (NUS-II Dataset), ${6 6 \\%}$ (BSL), 76% (MUGD Set 1), 80% (MUGD Set 2), 97% (MUGD Set 3), 96% (MUGD Set 4), 86% (MUGD Set 5), 97% (ASL Digit), 62% (ASL Static), ${7 4 \\%}$ (NUS-II Dataset), ${6 6 \\%}$ (BSL), and 79% (HG-14), respectively, which is better compared to the state-of-the-art methods.


  • HyFiNet: Hybrid feature attention network for hand gesture recognition
    Gopa Bhaumik, Monu Verma, Mahesh Chandra Govil, and Santosh Kumar Vipparthi
    Springer Science and Business Media LLC

  • Local Neighborhood Average Pattern: A Handcrafted Feature Descriptor for Hand Gesture Recognition
    Arti Bahuguna, Shalom Ben Tenzing Namchyo, Deepak Kumar Chaudhary, Gopa Bhaumik, and Mahesh Chandra Govil
    IEEE
    This paper proposes a handcrafted feature-based descriptor namely Local neighborhood average pattern (LNAP) for static hand gesture recognition. The fact, that the local descriptors are important in numerous computer vision applications and show great performance cannot be overstated. This is accentuated further in difficult environments. This is the major driving force behind continued research in this field. We developed a feature descriptor LNAP in this paper, with the aim of extracting complete microstructural features achieved by evaluating excitation in different ways and directional relevant data based on connections between pixels taken at various spatial configurations inside each 3 × 3 neighborhood. An LNAP descriptor represents the structure of hand textures in a simple and compact coding manner, resulting in its unique code in less time and memory than existing approaches. The proposed LNAP descriptor extracts the dominant features from the hand region which are further classified using SVM. The proposed LNAP's performance is assessed using three benchmark datasets: Massey University Dataset (MUGD), ASL Digit Datasets, and Ouhands Dataset in respect of accuracy and F1-score and found to achieve an accuracy of 93% (MUGD Set1), 96% (MUGD Set2), 92 % (MUGD Set 3), 89% (MUGD Set4), 71% (MUGD Set5), 99%, and 47% respectively. The experimental findings show that the suggested LNAP produces better outcomes than existing techniques.

  • ReEDNet-An Encoder–Decoder Framework for Single Image Dehazing
    Konark Keshaw, Abhishek Pandey, Gopa Bhaumik, and M C Govil
    Springer Nature Singapore


  • Att-PyNet: An Attention Pyramidal Feature Network for Hand Gesture Recognition
    Gopa Bhaumik, Monu Verma, Mahesh Chandra Govil, and Santosh Kumar Vipparthi
    Springer Singapore

  • Recognition of Hasta Mudra Using Star Skeleton—Preservation of Buddhist Heritage
    Gopa Bhaumik and Mahesh Chandra Govil
    Pleiades Publishing Ltd
    Nonverbal communication primarily by the way of hand gestures is as old as human evolution. Before languages were developed and texts, which came much after that, hand gestures were the only way of human interaction. And hence in historical artefacts across various civilizations and religions across the world hand gestures play a predominant role, some more than others. While selecting a subject for the application of this research we wanted to zero in on a practice or religion where non-verbal communication is a prevalent part and hence our inclination towards Buddhism. In Buddhism, hand gestures (mudras) are considered as a sacred gesture that represent the different Buddha deities and their significance. The article proposes a system that identify the Buddhist hand gesture (mudras) using computer-aided technology. The system comprises a preprocessing stage, which creates a contour plot of the image to obtain the boundary of the region of interest. The features are extracted by generating a star skeleton from the preprocessed image. The star skeleton calculated by considering the local maxima of the distance signal obtained by joining the centroid with the boundary pixels describes the mudras. Each of these mudras has a different star skeleton. The star skeletons computed from the known sample images are used to build a database for the recognition system. The recognition is achieved by choosing the template with the most similar skeleton retrieved from the database.

  • CrossFeat: Multi-scale Cross Feature Aggregation Network for Hand Gesture Recognition
    Gopa Bhaumik, Monu Verma, Mahesh Chandra Govil, and Santosh Kumar Vipparthi
    IEEE
    Hand gestures are considered as an effective means of communication in the field of Human-computer interaction. However, the design of an efficient hand gesture recognition (HGR) system is still a challenging task owing to a plethora of complexities such as cluttered background, illumination changes, and occlusion in a real-world environment. The paper proposes a lightweight CNN based network named CrossFeat: Multi-scale Cross Feature Aggregation network for explicit hand gesture recognition (HGR). CrossFeat employs multi-scale convolutional layers and preserves the spatial features from the hand gesture region. The use of multi-scale filters: 1 × 1, 3 × 3, 5 × 5 and 7 × 7 allow the network to learn granular and coarse edges from the different regions of the hand gestures. These complementary features enhance the learning ability of the network. Moreover, the cross-layer connectivity enables the gradient information to reach the top layers and prevent it from diminishing in the upstream layers. The proposed network is investigated on three benchmark datasets: ASL Finger Spelling, NUS-I and NUS-II. The experimental results and analysis show that the aggregation of multi-scale and cross features enhances the performance of the HGR system compared to the existing networks.


  • EXTRA: An Extended Radial Mean Response Pattern for Hand Gesture Recognition
    Gopa Bhaumik, Monu Verma, M C Govil, and S K Vipparthi
    IEEE
    Hand gesture recognition (HGR) has gained significant attention in recent year due to its varied applicability and ability to interact with machines efficiently. Hand gestures provide a way of communication for hearing-impaired persons. The HGR is a quite challenging task as its performance is influenced by various aspects such as illumination variations, cluttered backgrounds, spontaneous capture, multi-view etc. Thus, to resolve these issues in this paper, we propose an extended radial mean response (EXTRA) pattern for hand gesture recognition. The EXTRA pattern encodes the intensity variations by establishing a reconciled relationship between local neighboring pixels located at two radials r1 and r2. The gradient information between radials preserves the transitional texture that enhances the robustness to deal with illuminations changes. Moreover, the EXTRA pattern holds extensive radial information, thus it can conserve both high level and micro level edge variations that filter hand posture texture from the cluttered background. Furthermore, the mean responsive relationship between adjacency radial pixels improves robustness to noise conditions. The proposed technique is evaluated on three standard datasets viz NUS hand posture dataset-I, MUGD and Finger Spelling dataset. The experimental results and visual representations show that the proposed technique performs better than the existing algorithms for the purpose intended.

  • Buddhist Hasta Mudra Recognition Using Morphological Features
    Gopa Bhaumik and Mahesh Chandra Govil
    Springer Singapore
    Mudras are considered as spiritual gestures in the religious sense and hold a very important place in the cultural and spiritual space in India. Images are the symbolic representations of divinity in religious artwork and their origins are conveyed through the religions and spiritual beliefs. Such gestures also have some specific meaning in the Buddhist religion. It refers to some of the events in the life of Buddha or denotes special characteristics of the Buddha deities. In recent years, automatic identification of these gestures has gained a greater interest from the machine learning community. This would help to identify the various deities that exist in the Buddhist religion, leading to digital preservation of cultural heritage art. This paper provides a framework that recognizes the Buddhist hand gesture or Hasta Mudra. The morphological features are extracted from the gesture employing geometric parameters. The experimental results show that utilising geometric features and using k-Nearest Neighbor (kNN) as a classifier, an approximately 70% recognition rate is achieved.

  • Recognition Techniques in Buddhist Iconography and Challenges
    Gopa Bhaumik, Shefalika Ghosh Samaddar, and Arun Baran Samaddar
    IEEE
    The idea of preserving and disseminating cultural heritage digitally has led to the use of computing technology in preservation and determination of period-specific features of a artefact of cultural and historical importance. Pattern recognition techniques have been in use for quite some times for extracting feature information. One of the major requirement of archaeologists and art historians is to identify period of origin and age of ancient sculptures and artefacts for analysing their iconographic features and ensembles. Successful application of pattern recognition techniques in the field of iconography has recently received significant attention. A study has been made on the application of various pattern recognition techniques on the Buddhist iconography such as recognition of Thai Buddhist sculptures, Buddhist amulets, Thangka image retrieval, reconstruction of the statues by image analysis, hand gesture recognition etc. This paper provides a critical analysis of the research that have been carried out in the field of Buddhist Iconography as well the various techniques applied. The motivation for writing this paper is to report the review of the existing literature, analysis, the challenges in applications and solution in the subsequent research.

  • Analysis and detection of human faces by using minimum distance classifier for surveillance
    Gopa Bhaumik, Tanwi Mallick, Koyel Sinha Chowdhury, and Gautam Sanyal
    IEEE
    Visual Surveillance in dynamic scenes is one of the most active research areas. In this paper an algorithm has been proposed to detect human behaviours for visual surveillance. This method gives an efficient face recognition technique in dynamic scenario using Principal Component Analysis and Minimum distance classifier.

RECENT SCHOLAR PUBLICATIONS

  • Local Extrema Min-Max Pattern: A novel descriptor for extracting compact and discrete features for hand gesture recognition
    A Bahuguna, G Bhaumik, MC Govil
    Biomedical Signal Processing and Control 93, 106203 2024

  • Triple Stack Deep Variational Autoencoder For Improved Hand Gesture Recognition
    A Bahuguna, G Bhaumik, MC Govil
    2024 15th International Conference on Computing Communication and Networking 2024

  • SpAtNet: A spatial feature attention network for hand gesture recognition
    G Bhaumik, MC Govil
    Multimedia Tools and Applications 83 (14), 41805-41822 2024

  • Local Mean Directional Intensity Pattern: An Efficient Descriptor for Hand Gesture Recognition Using SVM Classification
    A Bahuguna, G Bhaumik, MC Govil
    International Conference on Intelligent Computing Systems and Applications 2023

  • Local Neighborhood Average Pattern: A Handcrafted Feature Descriptor for Hand Gesture Recognition
    A Bahuguna, SBT Namchyo, DK Chaudhary, G Bhaumik, MC Govil
    2023 Third International Conference On Secure Cyber Computing And 2023

  • HyFiNet: Hybrid feature attention network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    Multimedia Tools and Applications 82 (4), 4863-4882 2023

  • ExtriDeNet: an intensive feature extrication deep network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    The Visual Computer 38 (11), 3853-3866 2022

  • ReEDNet-An Encoder–Decoder Framework for Single Image Dehazing
    K Keshaw, A Pandey, G Bhaumik, MC Govil
    International Conference on Frontiers of Intelligent Computing: Theory and 2022

  • Att-PyNet: An Attention Pyramidal Feature Network for Hand Gesture Recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    Edge Analytics: Select Proceedings of 26th International Conference—ADCOM 2022

  • Att-PyNet: An Attention Pyramidal
    G Bhaumik, M Verma, MC Govil
    Edge Analytics: Select Proceedings of 26th International Conference—ADCOM 2022

  • Recognition of hasta mudra using star skeleton—preservation of buddhist heritage
    G Bhaumik, MC Govil
    Pattern Recognition and Image Analysis 31 (2), 251-260 2021

  • CrossFeat: multi-scale cross feature aggregation network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    2020 IEEE 15th international conference on industrial and information 2020

  • Conserving Thangka− A technical approach unto the preservation of Buddhist Thangka through automation
    G Bhaumik, MC Govil
    Digital Applications in Archaeology and Cultural Heritage 18, e00149 2020

  • EXTRA: an extended radial mean response pattern for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    2020 International conference on communication and signal processing (ICCSP 2020

  • Buddhist hasta mudra recognition using morphological features
    G Bhaumik, MC Govil
    Machine Learning, Image Processing, Network Security and Data Sciences 2020

  • Recognition techniques in Buddhist iconography and challenges
    G Bhaumik, SG Samaddar, AB Samaddar
    2018 international conference on advances in computing, communications and 2018

  • An algorithm for digital authentication of Buddha painting on Thangka
    G Bhaumik, SG Samaddar, AB Samaddar
    Science and Culture 84 (34), 129-133 2018

  • Analysis and detection of human faces by using minimum distance classifier for surveillance
    G Bhaumik, T Mallick, KS Chowdhury, G Sanyal
    2010 International Conference on Recent Trends in Information 2010

MOST CITED SCHOLAR PUBLICATIONS

  • HyFiNet: Hybrid feature attention network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    Multimedia Tools and Applications 82 (4), 4863-4882 2023
    Citations: 37

  • ExtriDeNet: an intensive feature extrication deep network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    The Visual Computer 38 (11), 3853-3866 2022
    Citations: 36

  • EXTRA: an extended radial mean response pattern for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    2020 International conference on communication and signal processing (ICCSP 2020
    Citations: 11

  • Analysis and detection of human faces by using minimum distance classifier for surveillance
    G Bhaumik, T Mallick, KS Chowdhury, G Sanyal
    2010 International Conference on Recent Trends in Information 2010
    Citations: 9

  • SpAtNet: A spatial feature attention network for hand gesture recognition
    G Bhaumik, MC Govil
    Multimedia Tools and Applications 83 (14), 41805-41822 2024
    Citations: 6

  • CrossFeat: multi-scale cross feature aggregation network for hand gesture recognition
    G Bhaumik, M Verma, MC Govil, SK Vipparthi
    2020 IEEE 15th international conference on industrial and information 2020
    Citations: 6

  • Local Extrema Min-Max Pattern: A novel descriptor for extracting compact and discrete features for hand gesture recognition
    A Bahuguna, G Bhaumik, MC Govil
    Biomedical Signal Processing and Control 93, 106203 2024
    Citations: 5

  • Recognition techniques in Buddhist iconography and challenges
    G Bhaumik, SG Samaddar, AB Samaddar
    2018 international conference on advances in computing, communications and 2018
    Citations: 5

  • Recognition of hasta mudra using star skeleton—preservation of buddhist heritage
    G Bhaumik, MC Govil
    Pattern Recognition and Image Analysis 31 (2), 251-260 2021
    Citations: 4

  • Conserving Thangka− A technical approach unto the preservation of Buddhist Thangka through automation
    G Bhaumik, MC Govil
    Digital Applications in Archaeology and Cultural Heritage 18, e00149 2020
    Citations: 4

  • Local Neighborhood Average Pattern: A Handcrafted Feature Descriptor for Hand Gesture Recognition
    A Bahuguna, SBT Namchyo, DK Chaudhary, G Bhaumik, MC Govil
    2023 Third International Conference On Secure Cyber Computing And 2023
    Citations: 3

  • Buddhist hasta mudra recognition using morphological features
    G Bhaumik, MC Govil
    Machine Learning, Image Processing, Network Security and Data Sciences 2020
    Citations: 3

  • An algorithm for digital authentication of Buddha painting on Thangka
    G Bhaumik, SG Samaddar, AB Samaddar
    Science and Culture 84 (34), 129-133 2018
    Citations: 2