The increasing need for robust digital signature verification systems has amplified interest in realistic online signature generation to counter digital forgeries. In this work, we propose a novel Decision Transformer based framework that learns Reinforcement Learning output to generate diverse online signatures. Departing from traditional RL approaches that rely on policy gradients or value function estimation, we formulate signature generation as a sequence-modeling problem. Our framework addresses varied free-form signature styles, demonstrating adaptability across linguistic and stylistic variations. Initially, an RL model generates signature trajectories, which are then fed to Decision Transformer, employing an autoregressive sequence modeling approach. To further personalize the generated signatures, we introduce a Q-learning-based module that produces user-specific variations while mitigating noise. By operating in an offline reinforcement learning setting, the proposed method reduces the dependency on extensive online interactions, improving scalability. Experimental results on a publicly available online signature dataset in multiple linguistic script styles show that our approach significantly outperforms traditional generative methods in terms of realism, variability, and mimicry accuracy. These results highlight the potential of Decision Transformers for structured sequence generation tasks beyond their conventional domains. Decision Transforme

Diabetes mellitus is a chronic metabolic disorder that necessitates frequent blood glucose monitoring, usually through painful and inconvenient methods. Volatile organic compounds (VOCs) in breath have been used as biomarkers for diabetes detection in non-invasive, Internet of Things (IoT)-based devices. Nevertheless, the cost, compactness, and mobility challenges of existing devices limit their general adoption. We present DiaBreath, a novel, affordable, non-invasive multi-sensor device for the early prediction of diabetes, solving these challenges. DiaBreath consists of (a) a breath analyzer containing MOS-based sensors, optimally selected via an ablation study to capture VOC responses (b) a feature engineering pipeline to to extract feature set, (c) a machine-learning model for reliable diabetes prediction, and (d) a simple user interface that generates prediagnostic diabetes reports. DiaBreath exhibits superior predictive power, with an accuracy of 97.6%, to enable efficient and scalable early diagnosis in public health centers, especially in resource-constrained settings. DiaBreath’s low cost and compact size make it highly adaptable for implementation in rural and underserved regions, where access to timely diabetes screening is limited. This technology improves non-invasive diabetes monitoring, making early diagnosis more cost-effective and accessible globally.

Denoising Diffusion Models (DDMs) are widely used for high-quality image generation and medical image segmentation but often rely on Unet-based architectures, leading to high computational overhead, especially with high-resolution images. This work proposes three NCA-based improvements for diffusion-based medical image segmentation. First, CBAMMedSegDiffNCA incorporates channel and spatial attention for improved segmentation. Second, Multi-MedSegDiffNCA uses a multilevel NCA framework to refine rough noise estimates generated by lower-level NCA models. Third, MultiCBAMMedSegDiffNCA combines these methods with a new RGB channel loss for semantic guidance. Evaluations on Lesion segmentation show that MultiCBAM-MedSegDiffNCA matches Unet-based model performance with a dice score of 87.84% while using 60-110 times fewer parameters and 5 times faster training, offering an efficient solution for low-resource medical settings.

Difficulty estimation of multiple-choice questions (MCQs) is crucial for creating effective educational assessments, yet remains underexplored in Indic languages like Hindi and Kannada due to the lack of comprehensive datasets. This paper addresses this gap by introducing two datasets, TEEMIL-H and TEEMIL-K, containing 4689 and 4215 MCQs, respectively, with manually annotated difficulty labels. We benchmark these datasets using state-of-the-art multilingual models and conduct ablation studies to analyze the effect of context, the impact of options, and the presence of the None of the Above (NOTA) option on difficulty estimation. Our findings establish baselines for difficulty estimation in Hindi and Kannada, offering valuable insights into improving model performance and guiding future research in MCQ difficulty estimation .

Identity details within an ECG is jointly situated within local and global features. The current methods for ECG recognition emphasize only on local or global details. They have also paid limited attention to unseen and cross-domain scenarios. Furthermore, there exists a lack of consensus on evaluation strategies. Thus, this paper introduces LGTraNet, a generalized architecture designed to establish baselines for securing personal identity using ECG biometrics in cross-domain scenarios. Our proposed model firstly extracts identity details at local temporal levels. The extracted features are then calibrated with globally details using a Self-Calibrated Normalizing Residual Network (SCNRNet). Finally, the refined local details are aggregated using a transformer model to formulate robust global identity representations. We evaluate LGTraNet over challenging cross-domain scenarios, such as cross-session and cross-database. To mitigate challenges in domain-shift, we also introduce an transfer learning based training strategy. Experimental study conducted on three benchmark datasets, ECG1D, MIT-BIH, and PTB, shows that the LGTraNet achieves significant performance in cross-domain settings, and outperforms state-of-the-art. Our code is available at: https://github.com/AmanVerma2307/LGTraNet.

The growing prevalence of AI-generated forgeries has intensified challenges in verifying handwritten signatures, a widely accepted form of biometric authentication. Existing state-of-the-art technologies have matured to authenticate signatures with high fidelity, there is now a pressing need to develop systems that can robustly detect and identify deepfake or AI-generated signatures. These synthetic forgeries, if undetected, can severely compromise security in digital systems. Therefore, to build more resilient verification systems, it is critical to create system which can learn discriminative features that uniquely characterize deepfake signatures. This paper presents Penformer, an online signature authentication system that detects both manual and AI generated forgeries. Combining structural features with log normal modeling of stroke and behavior dynamics with a multimodal transformer architecture, Penformer captures key spatial and temporal features. Experiments on openly available benchmark datasets and synthetically created datasets demonstrate SOTA results and show systems’ adaptability and effectiveness of digital signature verification against advanced forgery methods.

Signature being the most frequently used and widely accepted biometric has always attracted researchers due to complexities attached to its verification and analysis tasks. It can be categorized as offline or online based on the acquisition process. Online techniques are capable of capturing behavioral information. Signature possesses a unique spatial as well as temporal relation but suffers from large intra-class variation. Online signature verification techniques have been shown to yield better performance with respect to both intra-class variation as well as inter-class variation (forgery). This paper presents an online signature verification method where we propose: (i) a novel representation of the online signature data to video frames while maintaining structural and temporal information. (ii) a novel framework of spatio-temporal analysis for generated video frames to detect signature forgery. In this approach a method to extract long range temporal dependency is introduced which gives enhanced temporal context for better signature verification. We have conducted a series of experiments to train and validate our approach on the publicly available online signature datasets. Our proposed method outperforms the state-of-the-art, in online signature verification techniques and achieves an Equal Error Rate (EER) of 1.65% for skilled forgeries and 0.76% for random forgeries.

There is growing interest in developing virtual reality (VR) applications for mental health therapies. However, the investigation of the effectiveness of meditation in VR environments for mental health issues like stress remains mostly unexplored. This study seeks to fill this knowledge gap by investigating the influence of VR-guided Zen meditation (VRZM) on stress levels. 40 individuals were randomly divided into two between-subjects groups: one engaged in VRZM (N = 20), while the other received just a VR immersive environment without the Zen meditation's audio (VR; N = 20). The study explored the impact of VRZM on stress via EEG patterns and the Depression Anxiety Stress Scale - 21 (DASS - 21). The results indicated significantly reduced depression, anxiety, and stress levels in the VRZM group but not in the VR group. Moreover, VRZM induced a pronounced increase in the frontal alpha-to-temporal theta ratio, indicating enhanced relaxation, contrasting with no significant change in the VR group. The results suggested the effectiveness of VRZM meditation in promoting calmness and its potential efficacy in mental health interventions. We highlight the implications of VRZM for alleviating mental health problems like stress.

Multitasking requires rapid switching of attention and cognitive resources between different tasks in a dynamic environment, relying on cognitive processes, such as working memory, executive control, and selective attention. Although studies have investigated the efficacy of various neurobehavioral interventions in improving multitasking capabilities, the effects of longitudinal anodal transcranial direct current stimulation (tDCS) in enhancing multitasking performance have not been investigated. This research investigated the efficacy of 1mA anodal tDCS administered longitudinally on multitasking performance. 42 participants were randomly and equally divided into the experimental and placebo control conditions in this study conducted for 10 days. All participants executed two multitasking tasks on day 1 and received 1mA anodal/placebo tDCS during task training from day 2 to day 8. Various behavioral and neurophysiological measures have been measured. The findings revealed that tDCS had the propensity to augment multitasking capabilities in the trained task but had limited transfer capabilities. EEG-based brain connectivity analysis also revealed the formation of network hubs in the prefrontal and frontal regions, indicating enhanced cortical activation in the beta band. We intend to use these findings to design interventional frameworks to enhance multitasking performance using tDCS.

Anti-Seizure medications (also known as anticonvulsants or anti-epileptic medications) are a broad class of medicines mostly used to treat epileptic seizures. Objectively relating anticonvulsant identification with electroencephalogram (EEG) signals of the subject having a history of taking medication(s), can result in evaluating the effectiveness of the course of treatments for seizure-related illness, which is helpful in patient care. In this work, we propose a deep learning based method to discriminate the EEG recordings of the subjects who have used anti-epileptic medicines in the past from those who have not. Specifically, EEG recordings taken from the subjects are used to distinguish between the presence of the two common anticonvulsants, namely- keppra & dilantin; and the presence of no anticonvulsants at all. We extracted frequency domain features from the EEG recordings using the Fourier transform, and we then used the information as input to the proposed model. Frequency domain features are extracted since the frequency domain representation of EEG signals has some notable differences across the medication paradigms. We then suggest a model based on a convolutional neural network framework with attention to solve the three class (keppra, dilantin, and no medication) classification problem. The attention network aids in giving the features differential weights. The model's classification performance is shown to increase as a result of differential weighting, which makes it possible to focus more on the pertinent aspects needed for classification. We demonstrate that our approach yields improvements over the state-of-the-art results using the standard publicly available Temple University Hospital EEG Corpus (TUEG).

Long acquisition time (AQT) due to series acquisition of multi-modality MR images (especially T2 weighted images (T2WI) with longer AQT), though beneficial for disease diagnosis, is practically undesirable. We propose a novel deep network based solution to reconstruct T2W images from T1W images (T1WI) using an encoder-decoder architecture. The proposed learning is aided with semantic features by using multi-channel input with intensity values and gradient of image in two orthogonal directions. A reconstruction module (RM) augmenting the network along with a domain adaptation module (DAM) which is an encoder-decoder model built-in with sharp bottleneck module (SBM) is trained via modular training. The proposed network significantly reduces the total AQT with negligible qualitative artifacts and quantitative loss (reconstructs one volume in (~1 second). The testing is done on publicly available dataset with real MR images, and the proposed network shows (~ 1dB) increase in PSNR over SOTA.

Attention Deficit Hyperactivity Disorder (ADHD) is a behavior-based disorder that mainly occurs in young children. Resting-state fMRI data have been very popular for diagnosing brain disorders like Autism, ADHD, and schizophrenia, by network-based functional connectivity, since these disorders are associated with both individual brain regions and their connections. Finding patterns among regions of controls' brain and ADHD patients' discriminating brains, is a non-trivial task. For classification of ADHD, we propose an end-to-end lightweight CNN architecture with hierarchical representation learning i.e., HLGSNet. We extract 116 anatomical regions from each subject in both normal and patient conditions, and graphs are built with the help of temporal correlation between different regions, where each region is considered as a node. Following this, a Siamese graph convolution neural network with triplet loss has been trained for finding embeddings so that samples for the same class should have similar embeddings. Finally, along with a fully connected layer, the trained model has been fine-tuned for the classification task. Experiments have been carried out on publicly available ADHD-200 dataset with promising performance.

In this paper, we propose a statistical framework to prune feature maps in 1-D deep convolutional networks. SoundNet is a pre-trained deep convolutional network that accepts raw audio samples as input. The feature maps generated at various layers of SoundNet have redundancy, which can be identified by statistical analysis. These redundant feature maps can be pruned from the network with a very minor reduction in the capability of the network. The advantage of pruning feature maps, is that computational complexity can be reduced in the context of using an ensemble of classifiers on the layers of SoundNet. Our experiments on acoustic scene classification demonstrate that ignoring 89% of feature maps reduces the performance by less than 3% with 18% reduction in computational complexity.

We address the task of estimating depth from a single intensity image via a novel convolutional neural network (CNN) encoder-decoder architecture, which learns the depth information using example pairs of color images and their corresponding depth maps. The proposed model integrates residual connections within pooling and up-sampling layers, and hourglass networks which operate on the encoded features, thus processing these at various scales. Furthermore, the model is optimized under the constraints of perceptual as well as the mean squared error loss. The perceptual loss considers the high-level features, thus operating at a different scale of abstraction, which is complementary to the mean squared error loss. The improvements in qualitative and quantitative comparisons with state-of-the-art approaches demonstrate the effectiveness of our approach, even in presence of noise.

We propose an approach to reconstruct high field (7T) like MR images from low field (3T) MR images, which involves a merged convolutional autoencoder neural network. The network uses merge connections from downsampling encoder layers to cascade the input at upsampling layers of the decoder in order to preserve the local image details in transformed space. Further, we have used three channel input, defined by its image intensity values and corresponding gradient values in order to guide the discrimination. In terms of comparison with state-of-the-art, the proposed algorithm reconstruct 7T MR images with better tissue contrast, yields quantitative improvements, and has a significantly more efficient run-time. We also demonstrate the effectiveness of the approach with low training data and noise.

Depth map sensed by low-cost active sensor is often limited in resolution, whereas depth information achieved from structure from motion or sparse depth scanning techniques may result in a sparse point cloud. Achieving a high-resolution (HR) depth map from a low resolution (LR) depth map or densely reconstructing a sparse non-uniformly sampled depth map are fundamentally similar problems with different types of upsampling requirements. The first problem involves upsampling in a uniform grid, whereas the second type of problem requires an upsampling in a non-uniform grid. In this paper, we propose a new approach to address such issues in a unified framework, based on sparse representation. Unlike, most of the approaches of depth map restoration, our approach does not require an HR intensity image. Based on example depth maps, sub-dictionaries of exemplars are constructed, and are used to restore HR/dense depth map. In the case of uniform upsampling of LR depth map, an edge preserving constraint is used for preserving the discontinuity present in the depth map, and a pyramidal reconstruction strategy is applied in order to deal with higher upsampling factors. For upsampling of non-uniformly sampled sparse depth map, we compute the missing information in local patches from that from similar exemplars. Furthermore, we also suggest an alternative method of reconstructing dense depth map from very sparse non-uniformly sampled depth data by sequential cascading of uniform and non-uniform upsampling techniques. We provide a variety of qualitative and quantitative results to demonstrate the efficacy of our approach for depth map restoration.

We propose a novel classification framework to classify immunofluorescence images of HEp-2 cell specimens. We emphasize on using biologically motivated visual characteristics of classes, which we term as class-specific features. Given that the task involves less number of classes, a hierarchical verification based framework is employed, and is demonstrated to perform well. The current study focuses towards the classification of Homogeneous (H), Speckled (S) and Centromere (C) classes. The framework yields high classification rate with simple and efficient feature definitions. We also show encouraging performance for intermediate quality images, which represent early stage of diseases.

Lung 4D-CT provides important anatomical structure and motion information, which can be crucial in radiation therapy for lung cancer. However, radiation dose concerns limit the number of axial slices in 4D-CT, resulting in low superior-inferior resolution. We propose an approach to estimate the intermediate slices for resolution enhancement of 4D-CT. We explore the lung-motion-induced locally complimentary sampling information across respiratory phases, by using the deformation fields between 3D phase-volumes. For better robustness to noise and registration errors, we estimate the unknown intermediate slices in a patch-wise manner. To this end, we compute candidate patches from the available slices in different phases, based on the deformation field estimates. We then linearly combine the candidate patches, using weights computed by solving an h minimization problem. Unlike state-of-the-art methods, our deformation-driven patch-based approach requires a small number of inter-phase candidate patches, and yet outperforms these methods. This highlights the usefulness of considering deformation information in resolution enhancement of lung 4D-CT.

We propose an example-based approach for enhancing resolution of range-images. Unlike most existing methods on range-image superresolution (SR), we do not employ a colour image counterpart for the range-image. Moreover, we use only a small set of range-images to construct a dictionary of exemplars. Considering the importance of edges in range-image SR, our formulation involves an edge-based constraint to better weight appropriate patches from the dictionary in a sparse-representation framework. Moreover, realizing the need for large up-sampling factors in case of range-images, we follow a hierarchical strategy for estimating the high-resolution range-images. We demonstrate that our strategy yields considerable improvements over the state-of-the-art approaches for range-image SR.

Unrestricted camera motion and the ability to operate over a range of lens parameters are often desirable when using an off-the-shelf camera. Variations in intrinsic and extrinsic parameters induce defocus and pixel motion, both of which relate to scene structure. We propose a depth estimation approach by elegantly coupling the motion and defocus cues. We further advocate a natural extension of our framework for inpainting both depth and image, using the motion cue. Unlike traditional inpainting, our approach also considers defocus blur. This ensures that the image inpainting is coherent with respect to defocus. We use the belief propagation method in our estimation approach, which also handles occlusions and uses the color image segmentation cue.

We propose a technique to in paint large missing regions in range images. Such a technique can be used to restore degraded/occluded range maps. It can also serve to reconstruct dense depth maps from sparse measurements which can speed up the acquisition. Our method uses the visual cue from segmentation of an intensity image registered to the range image. Our approach enforces that pixels in the same segment should have similar range. Our simple strategy involves plane-fitting and local medians over segments to compute local energies for labeling unknown pixels. Our results exhibit high quality in painting with very low errors.

Under stereo settings, the twin problems of image superresolution (SR) and high-resolution (HR) depth estimation are intertwined. The subpixel registration information required for image superresolution is tightly coupled to the 3D structure. The effects of parallax and pixel averaging (inherent in the downsampling process) preclude a priori estimation of pixel motion for superresolution. These factors also compound the correspondence problem at low resolution (LR), which in turn affects the quality of the LR depth estimates. In this paper, we propose an integrated approach to estimate the HR depth and the SR image from multiple LR stereo observations. Our results demonstrate the efficacy of the proposed method in not only being able to bring out image details but also in enhancing the HR depth over its LR counterpart.

Given an off-the-shelf camera, one has the freedom to move the camera or play around with its intrinsic parameters such as zoom or aperture settings. We propose a framework for depth estimation from a set of calibrated images, captured under general camera motion and parameter variation. Our framework considers the practical trade-offs in a camera and hence essentially generalizes the more constrained areas such as lateral or axial stereo, shape from defocus/focus etc. We discuss practical issues where such an approach becomes important. We pose the problem in a MAP framework and compute the depth estimates efficiently using belief propagation (BP). We also incorporate the visibility consideration to handle occlusions. Moreover, we use the vital cue from color image segmentation to constrain the estimation process. Our results demonstrate the effectiveness of our approach to localize discontinuities and handle low-textured regions

Traditional stereo algorithms estimate disparity at the same resolution as the observations. In this work we address the problem of estimating disparity and occlusion information at a higher resolution (HR). We draw on the image formation model from the motion super-resolution domain to relate HR disparity and the observations. This approach estimates both the HR disparity and HR intensity. We minimize a suitably constructed cost function using graph cuts and iterated conditional modes (ICM) for disparity and intensity, respectively.