FISNET: A Learnable Fusion-Based Iris Segmentation Network Improving Robustness Across NIR and VIS Modalities Geetanjali Sharma, Gaurav Jaswal, Aditya Nigam, Raghavendra Ramachandra IEEE Access, 2025 Iris is one of the most distinctive biometric traits used for reliable identity verification in applications such as border control, secure access systems, and national ID programs. The primary challenge in iris recognition is the reliable segmentation of the iris region from the eye image. Segmenting irises captured under different imaging conditions is challenging for a single model due to variations in spectral features, texture, lighting conditions, and noise patterns between NIR and VIS images. To tackle this problem, we present Fused Iris Segmentation Network (FISNET) that combines segmentation maps from two models to achieve enhanced precision and accuracy. FISNET demonstrates robust generalizability across varying lighting, resolution, and sensor types, consistently outperforming individual models on all NIR and VIS datasets, including smartphone-captured images. The performance of FISNET was evaluated on CASIA-V4 subsets, Dark and Blue iris datasets, and the AFHIRIS dataset, achieving superior segmentation accuracy and recognition performance. The results demonstrate significant improvements over the IrisParseNet, PixlSegNet, and SAM model, achieving remarkable mIoU scores of 0.955, 0.930, 0.945, 0.955, 0.907, 0.815, 0.924, 0.913, 0.842, 0.852, 0.829, and 0.839 on the Lamp-V4, Interval-V4, Thousand-V4, Syn-V4, Twins-V4, UBIRIS-V2, BI-P1, BI-P2, DI-P1, DI-P2, DI-P3, and AFHIRIS-V1 datasets, respectively. Additionally, the Type-I error rate (E1) achieved exceptional results, with values of 0.0014, 0.0067, 0.0016, 0.0012, 0.0027, 0.0023, 0.0015, 0.0019, 0.0014, 0.0015, 0.0020, and 0.0069 across these datasets, further emphasizing the superiority of the proposed approach. Code is available at https://github.com/GeetanjaliGTZ/FIS-Net-NIR-and-VIS-Iris-Segmentation
A Novel CNN With Sliding Window Technique for Enhanced Classification of MI-EEG Sensor Data Kamal Singh, Nitin Singha, Gaurav Jaswal, Swati Bhalaik IEEE Sensors Journal, 2025 The major challenge in fully using the motor imagery (MI)-based brain-computer interface (MI-BCI) capabilities is accurately classifying the MI electroencephalography (MI-EEG) signals. Despite numerous advancements in signal processing and deep learning (DL) techniques, there is significant scope for improvement in the accuracy currently available in the state-of-the-art. This can be achieved by leveraging spatial and temporal features of MI-EEG signal. We propose SWCNet, a convolutional neural network (CNN)-based model, and integrate it with the sliding window technique to increase the accuracy. In this work, a new CNN architecture has been proposed to extract more features from data, whereas the sliding window technique enhances temporal features by augmenting the input sensor data along the temporal dimension. We have thoroughly evaluated the performance of SWCNet using subject-dependent and subject-independent approaches for four different datasets. Our analysis includes general accuracy metrics, an ablation study, a parametric sensitivity study, and a detailed classwise performance evaluation for the tongue, foot, left-hand, and right-hand movements. The proposed model achieves accuracies of 97.42%, 94.46%, 92.27%, and 90.82% for the BCI Competition IV-2a (BCIC-IV-2a), BCI Competition IV-2b (BCIC-IV-2b), High Gamma, and OpenBMI datasets, respectively. SWCNet outperforms the state-of-the-art methods with higher accuracy for all the datasets, demonstrating its superior generalizability. SWCNet holds promise in enhancing the effectiveness of BCI applications, especially in medical rehabilitation.
Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves Abhishek Tandon, Geetanjali Sharma, Gaurav Jaswal, Aditya Nigam, Raghavendra Ramachandra Proceedings 2025 IEEE Cvf Winter Conference on Applications of Computer Vision Workshops Wacvw 2025, 2025 We propose a trait-specific image generation method that models forehead creases geometrically using B-spline and Bezier curves. This approach ensures the realistic generation of both principal creases and non-prominent crease patterns, effectively constructing detailed and authentic forehead-crease images. These geometrically rendered images serve as visual prompts for a diffusion-based Edge-to-Image translation model, which generates corresponding mated samples. The resulting novel synthetic identities are then used to train a forehead-crease verification network. To enhance intra-subject diversity in the generated samples, we employ two strategies: (a) perturbing the control points of B-splines under defined constraints to maintain label consistency, and (b) applying image-level augmentations to the geometric visual prompts, such as dropout and elastic transformations, specifically tailored to crease patterns. By integrating the proposed synthetic dataset with real-world data, our method significantly improves the performance of forehead-crease verification systems under a cross-database verification protocol.
VREyeSAM: Virtual Reality Non-Frontal Iris Segmentation using Foundational Model with uncertainty weighted loss Geetanjali Sharma, Dev Nagaich, Gaurav Jaswal, Aditya Nigam, Raghavendra Ramachandra 2025 IEEE International Joint Conference on Biometrics Ijcb 2025, 2025 Advancements in virtual and head-mounted devices have introduced new challenges for iris biometrics, such as varying gaze directions, partial occlusions, and inconsistent lighting conditions. To address these obstacles, we present VREyeSAM, a robust iris segmentation framework specifically designed for images captured under both steady and dynamic gaze scenarios. Our pipeline includes a quality-aware pre-processing module that filters out partially or fully closed eyes, ensuring that only high-quality, fully open iris images are used for training and inference. In addition, we introduce an uncertainty weighted hybrid loss function that adaptively balances multiple learning objectives, enhancing the robustness of the model under diverse visual conditions. Using this approach, we evaluate VREyeSAM on the VRBiom dataset, where it achieves state-of-the-art performance with a Precision of 0.751, Recall of 0.870, F1-Score of 0.806, and a mean IoU of 0.647, significantly outperforming existing segmentation methods.
Finger biometrics for e-health security Gaurav Jaswal, Aditya Nigam, Ravinder Nath Handbook of Multimedia Information Security Techniques and Applications, 2019
CreaseGen: Generating Realistic Forehead-Creases via B-Splines, Reinforcement Learning and Diffusion Modeling A Tandon, A Sharma, G Sharma, G Jaswal, R Ramachandra, A Nigam Information Fusion, 103899 , 2025 2025
VREyeSAM: Virtual Reality Non-Frontal Iris Segmentation using Foundational Model with uncertainty weighted loss G Sharma, D Nagaich, G Jaswal, A Nigam, R Ramachandra IEEE International Joint Conference on Biometrics (IJCB) 2025 , 2025 2025 Citations: 1
Searching Identity details across Local-Global Features for Generalized Cross-Domain ECG Recognition S Kafley, A Verma, G Jaswal, A Bhavsar, A Nigam, R Ramachandra IEEE International Joint Conference on Biometrics (IJCB) 2025 , 2025 2025
Biometric Characteristics of Hand Gestures through Joint Decomposition of Cross-Subject and Cross-Session A Verma, G Jaswal, S Srirangarajan, SD Roy Pattern Recognition Letters (PRL) , 2025 2025
FISNET: a learnable fusion-based iris segmentation network improving Robustness across NIR and VIS modalities G Sharma, G Jaswal, A Nigam, R Ramachandra IEEE Access , 2025 2025 Citations: 3
Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves A Tandon, G Sharma, G Jaswal, A Nigam, R Ramachandra Proceedings of the Winter Conference on Applications of Computer Vision … , 2025 2025 Citations: 3
FC-IQA: Forehead-Creases Biometric Image Quality Assessment and Evaluation A Tandon, G Sharma, G Jaswal, R Ramachandra, A Nigam International Symposium on Visual Computing (ISVC), Las Vegas, NV, 2025 , 2025 2025
CLRecogEye : Curriculum learning towards exploiting convolution features for Dynamic Iris Recognition G Sharma, G Jaswal, A Nigam, R Ramachandra International Symposium on Visual Computing (ISVC), Las Vegas, NV, 2025. , 2025 2025
Color Residual Noise Patterns as Deep Features for Single-Image Morphing Attack Detection N Shastry, R Raghavendra, S Venkatesh, G Jaswal 10th IAPR-endorsed International Conference on Computer Vision and Image … , 2025 2025
A novel CNN with sliding window technique for enhanced classification of MI-EEG sensor data K Singh, N Singha, G Jaswal, S Bhalaik IEEE Sensors Journal 25 (1), 4777-4786 , 2025 2025 Citations: 9
Voice signals feature extraction and classification of bedridden patients N Kushwaha, N Mishra, RS Lalawat, G Jaswal, VK Gupta, PK Padhy 2024 International Conference on Communication, Control, and Intelligent … , 2024 2024 Citations: 1
A Comparative Analysis of EEG Signals Using PSD, FFT and Wavelet Transform Methods N Mishra, G Jaswal, N Kushwaha, VK Gupta, RS Lalawat, PK Padhy 2024 International Conference on Communication, Control, and Intelligent … , 2024 2024 Citations: 2
Impact of iris pigmentation on performance bias in visible iris verification systems: A comparative study G Sharma, A Tandon, G Jaswal, A Nigam, R Ramachandra International Conference on Pattern Recognition, 343-356 , 2024 2024 Citations: 6
Federated Learning Approaches for Intrusion Detection Systems: An Overview AK Nair, J Sahoo, G Jaswal Federated Learning, 131-152 , 2024 2024
Adopting Federated Learning for Software-Defined Networks AK Nair, J Sahoo, G Jaswal Federated Learning, 77-105 , 2024 2024
Multi-spectral Sensing to Detect Patterned/Textured Iris Contact Lens Attacks Using Deep Iris Features R Ramachandra, S Venkatesh, G Jaswal in 9th International Conference on Computer Vision and Image Processing … , 2024 2024 Citations: 1
Synthetic Forehead-creases Biometric Generation for Reliable User Verification A Tandon, G Sharma, G Jaswal, A Nigam, R Ramachandra IEEE International Joint Conference on Biometrics (IJCB 2024) , 2024 2024 Citations: 4
Mobile_FL: A streamlined FL framework for process optimisation via client clustering using rough c-means algorithm AK Nair, J Sahoo, LR Cenkeramaddi, G Jaswal, ED Raj Proceedings of the 10th ACM Cyber-Physical System Security Workshop 2024, 88-97 , 2024 2024 Citations: 3
Learning joint local-global iris representations via spatial calibration for generalized presentation attack detection G Jaswal, A Verma, SD Roy, R Ramachandra IEEE Transactions on Biometrics, Behavior, and Identity Science 6 (2), 195-208 , 2024 2024 Citations: 7
Quantifying Biometric Characteristics of Hand Gestures through Feature Space Probing and Identity-Level Cross-Gesture Disentanglement A Verma, G Jaswal, S Srirangarajan, SD Roy 18th IEEE International Conference on Automatic Face and Gesture Recognition … , 2024 2024 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
Torrefaction: a sustainable method for transforming of agri-wastes to high energy density solids (biocoal) S Negi, G Jaswal, K Dass, K Mazumder, S Elumalai, JK Roy Reviews in Environmental Science and Bio/Technology, Springer, https://link … , 2020 2020 Citations: 111
Knuckle print biometrics and fusion schemes--overview, challenges, and solutions G Jaswal, A Kaul, R Nath ACM Computing Surveys (CSUR) 49 (2), 1-46 , 2016 2016 Citations: 99
PVSNet: Palm vein authentication siamese network trained using triplet loss and adaptive hard mining by learning enforced domain specific features D Thapar, G Jaswal, A Nigam, V Kanhangad 2019 IEEE 5th international conference on identity, security, and behavior … , 2019 2019 Citations: 80
PixISegNet: Pixel Level Iris Segmentation Network using Convolutional Encoder-Decoder with Stacked Hourglass Bottleneck R Ranjan Jha, G Jaswal, G Divij, S Shreshth, A Nigam IET Biometrics , 2019 2019 Citations: 51
Single-sensor hand-vein multimodal biometric recognition using multiscale deep pyramidal approach S Bhilare, G Jaswal, V Kanhangad, A Nigam Machine Vision and Applications 29 (8), 1269-1286 , 2018 2018 Citations: 48
Selection of optimized features for fusion of palm print and finger knuckle based person authentication G Jaswal, R Poonia Expert Systems , 2020 2020 Citations: 46
Gait metric learning siamese network exploiting dual of spatio-temporal 3D-CNN intra and LSTM based inter gait-cycle-segment features D Thapar, G Jaswal, A Nigam, C Arora Pattern Recognition Letters 125, 646-653 , 2019 2019 Citations: 46
DeepKnuckle: revealing the human identity G Jaswal, A Nigam, R Nath Multimedia Tools and Applications 76 (18), 18955-18984 , 2017 2017 Citations: 44
Texture based palm Print recognition using 2-D Gabor filter and sub space approaches G Jaswal, R Nath, A Kaul IEEE International Conference on Signal Processing, Computing and Control … , 2015 2015 Citations: 39
Multiple feature fusion for unconstrained palm print authentication G Jaswal, A Kaul, R Nath Computers and Electrical Enginnering 72, 53-78 , 2018 2018 Citations: 38
Towards the generation of synthetic images of palm vein patterns: A review EH Salazar-Jurado, R Hernández-García, K Vilches-Ponce, RJ Barrientos, ... Information Fusion 89, 66-90 , 2023 2023 Citations: 36
QRS detection using wavelet transform G Jaswal, R Parmar, A Kaul International Journal of Engineering and Advanced Technology (IJEAT) 1 (6 … , 2012 2012 Citations: 31
Multimodal biometric authentication system using hand shape, palm print, and hand geometry G Jaswal, A Kaul, R Nath Computational Intelligence: Theories, Applications and Future Directions … , 2018 2018 Citations: 28
FKIMNet: A Finger Dorsal Image Matching Network Comparing Component (Major, Minor and Nail) Matching with Holistic (Finger Dorsal) Matching D Thapar, G Jaswal, A Nigam 2019 International Joint Conference on Neural Networks (IJCNN), 1-8 , 2019 2019 Citations: 26
AI and Deep Learning in Biometric Security: Trends, Potential, and Challenges G Jaswal, V Kanhangad, R Ramachandra https://www.routledge.com/AI-and-Deep-Learning-in-Biometric-Security-Trends … , 2020 2020 Citations: 21
Single-Shell to Multi-Shell dMRI Transformation using Spatial and Volumetric Multilevel Hierarchical Reconstruction Framework RR Jha, G Jaswal, A Bhavsar, A Nigam Magnetic Resonance Imaging , 2022 2022 Citations: 17
HLGSNet: Hierarchical and Lightweight Graph Siamese Network with Triplet Loss for fMRI-based Classification of ADHD RR Jha, J Gaurav, N Aditya, B Arnav, P Sudhir K, K Rathish The International Joint Conference on Neural Networks (IJCNN) , 2020 2020 Citations: 17
AI-biometric driven Smartphone App for strict Post-COVID Home Quarantine Management G Jaswal, R Bharadwaj, D Thapar, P Goyal, K Tiwari, A Nigam IEEE Consumer Electronics Magazine , 2020 2020 Citations: 16
Content Based Image Retrieval–A Literature Review G Jaswal, A Kaul National Conference on Computing Communication and Control , 2009 2009 Citations: 16
Content based Image Retrieval using Color Space Approaches G Jaswal, A Kaul, R Parmar International Journal of Engineering and Advanced Technology (IJEAT) ISSN … , 2012 2012 Citations: 15
