Papers by Soumyabrata Dey
arXiv (Cornell University), Sep 30, 2023
Liveness Detection (LivDet) is an international competition series open to academia and industry ... more Liveness Detection (LivDet) is an international competition series open to academia and industry with the objective to assess and report state-of-the-art in Presentation Attack Detection (PAD). LivDet-2023 Noncontact Fingerprint is the first edition of the noncontact fingerprint-based PAD competition for algorithms and systems. The competition serves as an important benchmark in noncontact-based fingerprint PAD, offering (a) independent assessment of the state-of-the-art in noncontact-based fingerprint PAD for algorithms and systems, and (b) common evaluation protocol, which includes finger photos of a variety of Presentation Attack Instruments (PAIs) and live fingers to the biometric research community (c) provides standard algorithm and system evaluation protocols, along with the comparative analysis of state-of-the-art algorithms from academia and industry with both old and new android smartphones. The winning algorithm achieved an APCER of 11.35% averaged over all PAIs and a BPCER of 0.62%. The winning system achieved an APCER of 13.0.4%, averaged over all PAIs tested over all the smartphones, and a BPCER of 1.68% over all smartphones tested. Four-finger systems that make individual finger-based PAD decisions were also tested. The dataset used for competition will be available 1 to all researchers as per data share protocol.
Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP... more Wikipedia articles are a widely used source of training data for Natural Language Processing (NLP) research, particularly as corpora for lowresource languages like Arabic. However, it is essential to understand the extent to which these corpora reflect the representative contributions of native speakers, especially when many entries in a given language are directly translated from other languages or automatically generated through automated mechanisms. In this paper, we study the performance implications of using inorganic corpora that are not representative of native speakers and are generated through automated techniques such as bot generation or automated template-based translation. The case of the Arabic Wikipedia editions gives a unique case study of this since the Moroccan Arabic Wikipedia edition (ARY) is small but representative, the Egyptian Arabic Wikipedia edition (ARZ) is large but unrepresentative, and the Modern Standard Arabic Wikipedia edition (AR) is both large and more representative. We intrinsically evaluate the performance of two main NLP upstream tasks, namely word representation and language modeling, using word analogy evaluations and fillmask evaluations using our two newly created datasets: Arab States Analogy Dataset (ASAD) and Masked Arab States Dataset (MASD). We demonstrate that for good NLP performance, we need both large and organic corpora; neither alone is sufficient. We show that producing large corpora through automated means can be a counter-productive, producing models that both perform worse and lack cultural richness and meaningful representation of the Arabic language and its native speakers.
Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems
2023 11th International Workshop on Biometrics and Forensics (IWBF)
Real-Time Hand Gesture Identification in Thermal Images
Lecture Notes in Computer Science, 2022
arXiv (Cornell University), Mar 2, 2023
Hand gesture detection is a well-explored area in computer vision with applications in various fo... more Hand gesture detection is a well-explored area in computer vision with applications in various forms of Human-Computer Interactions. In this work, we propose a technique for simultaneous hand gesture classification, handedness detection, and hand keypoints localization using thermal data captured by an infrared camera. Our method uses a novel deep multi-task learning architecture that includes shared encoderdecoder layers followed by three branches dedicated for each mentioned task. We performed extensive experimental validation of our model on an in-house dataset consisting of 24 users' data. The results confirm higher than 98% accuracy for gesture classification, handedness detection, and fingertips localization, and more than 91% accuracy for wrist points localization.
Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems
arXiv (Cornell University), Mar 9, 2023
Interpretable and High-Performance Hate and Offensive Speech Detection
Lecture Notes in Computer Science, 2022
End-to-End Latency Optimization of Multi-view 3D Reconstruction for Disaster Response
2022 10th IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud)
Cornell University - arXiv, Jun 26, 2022
The spread of information through social media platforms can create environments possibly hostile... more The spread of information through social media platforms can create environments possibly hostile to vulnerable communities and silence certain groups in society. To mitigate such instances, several models have been developed to detect hate and offensive speech. Since detecting hate and offensive speech in social media platforms could incorrectly exclude individuals from social media platforms, which can reduce trust, there is a need to create explainable and interpretable models. Thus, we build an explainable and interpretable high performance model based on the XGBoost algorithm, trained on Twitter data. For unbalanced Twitter data, XGboost outperformed the LSTM, AutoGluon, and ULMFiT models on hate speech detection with an F1 score of 0.75 compared to 0.38 and 0.37, and 0.38 respectively. When we down-sampled the data to three separate classes of approximately 5000 tweets, XGBoost performed better than LSTM, AutoGluon, and ULMFiT; with F1 scores for hate speech detection of 0.79 vs 0.69, 0.77, and 0.66 respectively. XGBoost also performed better than LSTM, AutoGluon, and ULMFiT in the downsampled version for offensive speech detection with F1 score of 0.83 vs 0.88, 0.82, and 0.79 respectively. We use Shapley Additive Explanations (SHAP) on our XGBoost models' outputs to makes it explainable and interpretable compared to LSTM, AutoGluon and ULMFiT that are black-box models.
DNN-based Denial of Quality of Service Attack on Software-defined Hybrid Edge-Cloud Systems
2022 IEEE 22nd Annual Wireless and Microwave Technology Conference (WAMICON)
Attributed graph distance measure for automatic detection
MultiMedia Modeling, 2019
Natural surfaces offer the opportunity to provide augmented reality interactions in everyday envi... more Natural surfaces offer the opportunity to provide augmented reality interactions in everyday environments without the use of cumbersome body-mounted equipment. One of the key techniques of detecting user interactions with natural surfaces is the use of thermal imaging that captures the transmitted body heat onto the surface. A major challenge of these systems is detecting user swipe pressure on different material surfaces with high accuracy. This is because the amount of transferred heat from the user body to a natural surface depends on the thermal property of the material. If the surface material type is known, these systems can use a material-specific pressure classifier to improve the detection accuracy. In this work, we address to solve this problem as we propose a novel approach that can detect material type from a user's thermal finger impression on a surface. Our technique requires the user to touch a surface with a finger for 2 s. The recorded heat dissipation time series of the thermal finger impression is then analyzed in a classification framework for material identification. We studied the interaction of 15 users on 7 different material types, and our algorithm is able to achieve 74.65% material classification accuracy on the test data in a user-independent manner.
Development of a Multilingual Recognition Engine for Automatic Interpretation of Handwritten Form Documents
Recognition of Pincodes from Indian Postal Documents
Soft Computing
Recognition of Pincodes from Indian Postal Documents Subhadip Basu, Sankha Subhra Seth, Pradipta ... more Recognition of Pincodes from Indian Postal Documents Subhadip Basu, Sankha Subhra Seth, Pradipta Sarkar, Biplab Das, Soumyabrata Dey andSoumili Ghosh MCKV Institute of Engineering, Liluah, Howrah Abstract Recognition of handwritten text documents is still ...
Reviewed by
doi: 10.3389/fnsys.2012.00075 Exploiting the brain’s network structure in identifying ADHD subjects
ADHD Classification Using Bag of Words Approach on Network Features
Attention Deficit Hyperactivity Disorder (ADHD) is receiving lots of attention nowadays mainly be... more Attention Deficit Hyperactivity Disorder (ADHD) is receiving lots of attention nowadays mainly because it is one of the common brain disorders among children and not much information is known about the cause of this disorder. In this study, we propose to use a novel approach for automatic classification of ADHD conditioned subjects and control subjects using functional Magnetic Resonance Imaging (fMRI) data of resting state brains. For this purpose, we compute the correlation between every possible voxel pairs within a subject and over the time frame of the experimental protocol. A network of voxels is constructed by representing a high correlation value between any two voxels as an edge. A Bag-of-Words (BoW) approach is used to represent each subject as a histogram of network features; such as the number of degrees per voxel. The classification is done using a Support Vector Machine (SVM). We also investigate the use of raw intensity values in the time series for each voxel. Here, ...
Building predictive models of healthcare costs with open healthcare data
2020 IEEE International Conference on Healthcare Informatics (ICHI), 2020
Due to rapidly rising healthcare costs worldwide, there is significant interest in controlling th... more Due to rapidly rising healthcare costs worldwide, there is significant interest in controlling them. An important aspect concerns price transparency, as preliminary efforts have demonstrated that patients will shop for lower costs, driving efficiency. This requires the data to be made available, and models that can predict healthcare costs for a wide range of patient demographics and conditions.We present an approach to this problem by developing a predictive model using machine-learning techniques. We analyzed de-identified patient data from New York State SPARCS (statewide planning and research cooperative system), consisting of 2.3 million records in 2016. We built models to predict costs from patient diagnoses and demographics. We investigated two model classes consisting of sparse regression and decision trees. We obtained the best performance by using a decision tree with depth 10. We obtained an R2 value of 0.76, which is better than the values reported in the literature for ...
Natural surfaces offer the opportunity to provide augmented reality interactions in everyday envi... more Natural surfaces offer the opportunity to provide augmented reality interactions in everyday environments without the use of cumbersome body-mounted equipment. One of the key techniques of detecting user interactions with natural surfaces is the use of thermal imaging that captures the transmitted body heat onto the surface. A major challenge of these systems is detecting user swipe pressure on different material surfaces with high accuracy. This is because the amount of transferred heat from the user body to a natural surface depends on the thermal property of the material. If the surface material type is known, these systems can use a material-specific pressure classifier to improve the detection accuracy. In this work, we address to solve this problem as we propose a novel approach that can detect material type from a user’s thermal finger impression on a surface. Our technique requires the user to touch a surface with a finger for 2 s. The recorded heat dissipation time series o...
A novel entropy-based texture inpainting algorithm
Signal, Image and Video Processing
Image inpainting is the process of restoring a lost or damaged portion of an image. Inpainting of... more Image inpainting is the process of restoring a lost or damaged portion of an image. Inpainting of an image that contains texture remains a particularly challenging problem. We aim to propose an algorithm to inpaint a textured image accurately using a single image. The main idea is to segment the given image, based on its texture. In this work, we propose a novel local energy approach, in combination with the k -means algorithm to segment the given image, based on its texture. We use this segmentation result to restrict the search of matching pixels to only-relevant segments. Moreover, we use the entropy-based dissimilarity parameter to find matching pixels, instead of the $$\ell ^2$$ ℓ 2 distance. The restriction of the search area improves the efficiency, and the use of the proposed dissimilarity parameter provides a better way to compare textures, giving improved inpainting for textured images.
Personalized cumulative UV tracking on mobiles & wearables
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2017
Maintaining a balanced Ultra Violet (UV) exposure level is vital for a healthy living as the exce... more Maintaining a balanced Ultra Violet (UV) exposure level is vital for a healthy living as the excess of UV dose can lead to critical diseases such as skin cancer while the absence can cause vitamin D deficiency which has recently been linked to onset of cardiac abnormalities. Here, we propose a personalized cumulative UV dose (CUVD) estimation system for smartwatch and smartphone devices having the following novelty factors; (a) sensor orientation invariant measurement of UV exposure using a bootstrap resampling technique, (b) estimation of UV exposure using only light intensity (lux) sensor (c) optimal UV exposure dose estimation. Our proposed method will eliminate the need for a dedicated UV sensor thus widen the user base of the proposed solution, render it unobtrusive by eliminating the critical requirement of orienting the device in a direction facing the sun. The system is implemented on android mobile platform and validated on 1200 minutes of lux and UV index (UVI) data collec...
Uploads
Papers by Soumyabrata Dey