Nibaran Das

Nibaran Das
Jadavpur University | JU · Department of Computer Science and Engineering

PhD

About

249
Publications
77,459
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,647
Citations
Introduction
My current research interests include Optical Character Recognition, Deep Learning, Computer Vision, Medical Imaging, and Optimization algorithms.
Additional affiliations
August 2018 - November 2019
Jadavpur University
Position
  • Professor (Associate)
July 2006 - present
Jadavpur University
Position
  • Professor (Assistant)

Publications

Publications (249)
Preprint
Quantum neural networks are deemed suitable to replace classical neural networks in their ability to learn and scale up network models using quantum-exclusive phenomena like superposition and entanglement. However, in the noisy intermediate scale quantum (NISQ) era, the trainability and expressibility of quantum models are yet under investigation....
Preprint
Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains when training with new domains. We illuminate this current neural network model weakness and develop a forgetting-resistant increment...
Article
Author verification is challenging because of the diversity in writing styles. We propose an enhanced handwriting verification method that combines handcrafted and automatically extracted features. The method uses a genetic algorithm to reduce the dimensionality of the feature set. We consider offline Bangla handwriting content and evaluate the pro...
Article
Full-text available
In all developing and developed countries globally, skin diseases are becoming a prevalent health problem for humans of all age groups. Skin diseases create anxiety, affect mental health, worsen working life, and sometimes cause social isolation. Detecting skin diseases in the early stage is very important because early treatment can be helpful in...
Article
Full-text available
Text localization and detection within natural scene images have generated significant interest among researchers due to their inherent complexity and various real-life applications. In the last few decades, various methodologies have been developed for localization and detection of wild scene text regions. Among them, Maximally Stable Extremal Reg...
Chapter
Multilingual natural scene text recognition is difficult due to its complex text font style, difficult image background, multilingual text formats, etc. In vision-based applications, natural scene text plays an important role in industrial automation, robot navigation, application software for visually impaired persons, instant translation of multi...
Chapter
In recent decades, blind feature-based source camera detection has drawn a lot of attention. In literature, researchers used a specific sort of distortion, such as vignetting effects, chromatic aberration, and radial lens distortion, etc., to distinguish between different camera models. Therefore, it becomes specific to the distortions present in t...
Chapter
Audio and video conferencing apps like Google meet, Zoom, Mobile call conference are becoming more and more popular. Conferencing apps are used not only by professionals for remote work, but also for keeping social relations. Present situation demands understanding of these platforms in details and extract useful features to recognize them. Identif...
Chapter
Automated cytology image classification using computer-aided diagnosis (CAD)-based system is an important task for diagnosing cancer at early stage. For the last few decades, researchers have remain involved in the research of cytology domain. Optimal features selection is an utmost importance to enhance the performance of cytology image classifica...
Article
Full-text available
This paper presents an unique audio database, we named it Multivariate Audio Database (MAuD), where audio data has been collected in real life scenarios. MAuD contains 229 audio files, each of duration approx 5 minutes, collected across different conferencing apps, spoken languages, background noises and discussion topics. Various audio conferencin...
Preprint
In literature, NAND and NOR are two logic gates that display functional completeness, hence regarded as Universal gates. So, the present effort is focused on exploring a library of universal gates in binary that are still unexplored in literature along with a broad and systematic approach to classify the logic connectives. The study shows that the...
Preprint
Full-text available
Handwriting analysis presents a formidable challenge, especially when dealing with languages like Bangla that lack extensive resources. Previous research on Bangla handwritten document recognition has focused on various levels, including page, block, line, and word analysis. However, the improvement of page-level recognition in this context remains...
Article
Full-text available
Over 500 K (per year) cervical cancer cases are reported with a high mortality rate (6–9%). Automatically detecting cervical cancer using the Computer-Aided Diagnosis (CAD) tool at an early stage is important since it leads to successful treatment as pathologists. In this paper, we propose a tool that classifies cervical cancer cases from Pap smear...
Chapter
An automatic recognition system is developed to identify six different vegetable species, Solanum melongena (eggplant), Abelmoschus esculentus (okra), Solanum tuberosum (potato), Raphanus sativus (radish), Solanum lycopersicum (tomato), and Daucus carota (carrot). It helps the specially abled persons to buy these vegetables in the market independen...
Article
Full-text available
This paper describes the effect of analysis window functions on the performance of Mel Frequency Cepstral Coefficient (MFCC) based speaker recognition (SR). The MFCCs of speech signal are extracted from the fixed length frames using Short Time Fourier Analysis (STFA) technique where an appropriate analysis window function is required to extract fra...
Article
Full-text available
Conceptual representations of images involving descriptions of entities and their relations are often represented using scene graphs. Such scene graphs can express relational concepts by using sets of triplets ⟨subject—predicate—object⟩. Instead of building dedicated models for scene graph generation, our model tends to extract the latent relationa...
Chapter
The limitations of domain dependence in neural networks and data scarcity are addressed in this paper by analyzing the problem of semi-supervised medical image classification across multiple visual domains using a single integrated framework. Under this premise, we learn a universal parametric family of neural networks, which share a majority of th...
Chapter
In this study, a voice enabled math tutor system is proposed that enables children to practice math problems on their own. For this, we have developed numerical sound dataset targeting the application. In the application, when the system is turned on, a math problem is generated, and the child will respond verbally to it. The system will categorize...
Preprint
Full-text available
Historical Document Image Binarization is a well-known segmentation problem in image processing. Despite ubiquity, traditional thresholding algorithms achieved limited success on severely degraded document images. With the advent of deep learning, several segmentation models were proposed that made significant progress in the field but were limited...
Article
In the present work, we have explored the potential of Copula-based ensemble of CNNs(Convolutional Neural Networks) over individual classifiers for malignancy identification in histopathology and cytology images. The Copula-based model that integrates three best performing CNN architectures, namely, DenseNet-161/201, ResNet-101/34, InceptionNet-V3...
Chapter
Development of complete OCR for handwritten document (HOCR) is a challenging task due to a wide variation in writing styles, cursiveness, and contrasts in captured text images. We introduce a new three-staged pipeline process consisting of a) text detection, b) text recognition, c) text to speech conversion for the development of successful HOCR of...
Chapter
In a multi script environment Script identification is essential prior to text recognition. Compared to document images, Script identification in natural scene images becomes a more challenging task due to complex backgrounds, intricate font styles, poor image quality etc. All this is in addition to the common problem of script recognition, related...
Article
The fisheries industry relies heavily on automatic fish species identification for its socio-economic well-being. Due to the similarity in shape and size of the major carps , it can be difficult to recognise them using morphological features. To recognise these species automatically, our proposed autoencoder network models have been applied to a fi...
Article
Full-text available
Object detection is one of the essential branches of computer vision. However, detecting objects in the natural scene is challenging due to various reasons, for example, different sizes of objects, overlapping and similarities of colour, the texture of different objects, etc. The visible spectrum is not suited for standard computer vision tasks in...
Article
With the advent of mobile and hand-held cameras, document images have found their way into almost every domain. Dewarping of these images for the removal of perspective distortions and folds is essential so that they can be understood by document recognition algorithms. For this, we propose an end-to-end CNN architecture that can produce distortion...
Article
Full-text available
Weber local descriptor (WLD) is applied for addressing the challenges in image/pattern problems, especially in computer vision and pattern recognition domains. In this paper, we review literature on theories and applications of WLD. Using WLD, we address the different challenges of image analysis and recognition features with respect to illuminatio...
Chapter
Full-text available
In this chapter, we discuss state-of-the-art deep learning models. We start with different types of deep learning models, where different learning objectives, CNN architectures, and models that are based on learning strategies are taken into account. Then we provide several different elements involved in deep learning models, such as data preproces...
Chapter
In this chapter, we mainly focus on the use of AI-driven tools for COVID-19 predictive modeling, screening, and decision-making. We first discuss prediction models, their merits, and pitfalls. We then review deep learning models for COVID-19 detection and/or screening (with experiments) by taking different dataset sizes into account, which is follo...
Chapter
This chapter provides a review of deep learning models/architectures. It covers a comprehensive review of basic neural networks, convolutional neural networks, and encode–decoder architecture.
Chapter
In the last three chapters, we have discussed the working principle of different CNN models that are popularly used in the domain of pattern recognition and/or object classification. Most of those models are considerably successful in medical diagnosis. In this chapter, we consider those tools and help readers understand cytology image analysis. We...
Chapter
The Covid-19 pandemic coupled with lockdown has nearly brought the world to a standstill. It has left both short and long-term impacts on the mental health of the children. The goal of this paper is to predict the changes in various mental health parameters such as health, emotion, behavior, maturity, and education. Our target research group is the...
Chapter
A deep learning based automatic identification system has been developed for three exotic carps, Cyprinus carpio (Common carp), Hypophthalmichthys molitrix (Silver carp), and Ctenopharyngodon idella (Grass carp). The system consists of four steps, namely, data collection, image pre-processing, image segmentation, and species identification. The ima...
Book
Deep Learning Models for Medical Imaging explains the concepts of Deep Learning (DL) and its importance in medical imaging and/or healthcare using two different case studies: a) cytology image analysis and b) coronavirus (COVID-19) prediction, screening, and decision-making, using publicly available datasets in their respective experiments. Of many...
Article
Full-text available
An array of features and methods are being developed over the past six decades for Speaker Identification (SI) and Speaker Verification (SV), jointly known as Speaker Recognition(SR). Mel Frequency Cepstral Coefficients (MFCC) is generally used as feature vectors in most of the cases because it gives higher accuracy compared to other features. The...
Article
Full-text available
Cervical cancer is one of the most deadly and common diseases among women worldwide. It is completely curable if diagnosed in an early stage, but the tedious and costly detection procedure makes it unviable to conduct population-wise screening. Thus, to augment the effort of the clinicians, in this paper, we propose a fully automated framework that...
Preprint
Full-text available
Cervical cancer is the fourth most common category of cancer, affecting more than 500,000 women annually, owing to the slow detection procedure. Early diagnosis can help in treating and even curing cancer, but the tedious, time-consuming testing process makes it impossible to conduct population-wise screening. To aid the pathologists in efficient a...
Preprint
Full-text available
Presently, Covid-19 is a serious threat to the world at large. Efforts are being made to reduce disease screening times and in the development of a vaccine to resist this disease, even as thousands succumb to it everyday. We propose a novel method of automated screening of diseases like Covid-19 and pneumonia from Chest X-Ray images with the help o...
Article
Full-text available
Videos – a high volume of texts – broadcast via different media, such as television and the internet. Since Optical Character Recognition (OCR) engines are script-dependent, script identification is a precursor. Other than that, video script identification is not trivial as we have difficult issues, such as low resolution, complex background, noise...
Preprint
Full-text available
Cervical cancer is one of the most deadly and common diseases among women worldwide. It is completely curable if diagnosed in an early stage, but the tedious and costly detection procedure makes it unviable to conduct population-wise screening. Thus, to augment the effort of the clinicians, in this paper, we propose a fully automated framework that...
Chapter
Multi-lingual script identification is a difficult task consisting of different language with complex backgrounds in scene text images. According to the current research scenario, deep neural networks are employed as teacher models to train a smaller student network by utilizing the teacher model’s predictions. This process is known as dark knowled...
Chapter
Colorectal cancer is one major cause of cancer-related death around the globe. Recent breakthroughs in deep learning have paved the way to apply it for the automation of histopathology images as a tool for computer-aided diagnosis of medical imaging. Here we have presented a novel state of the art classification model for classifying the colorectal...
Chapter
Object detection in natural scenes can be a challenging task. In many real-life situations, the visible spectrum is not suitable for traditional computer vision tasks. Moving outside the visible spectrum range, such as the thermal spectrum or the near-infrared (NIR) images, is much more beneficial in low visibility conditions, NIR images are very h...
Article
Full-text available
Detecting objects in natural scenes can be a very challenging task. In several real-life scenarios it is often found that visible spectrum is not ideal for typical computer vision tasks. Going beyond the range of visible light spectrum, such as the near infrared spectrum or the thermal spectrum allows us to capture many unique properties of objects...
Preprint
Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation. But this allows gradients to be distributed equally among all paths. The proposed approach guides the gradients of backpropagation along weakest concept representations. A weakness scores defines the class specific...
Article
Full-text available
Cytology is a branch of pathology that deals with the microscopic examination of cells for diagnosis of carcinoma or inflammatory conditions. In the present work, the term cytology is used to indicate solid organ cytology. Automation in cytology started in the early 1950s with an aim to reduce manual efforts in the diagnosis of cancer. The influx o...
Chapter
In this work, we present a novel method that uses convolutional neural networks (CNNs) for multi scale and multi spectral feature extraction. The model is not only limited to conventional spatial domain representation but also multilevel two dimensional discrete Haar wavelet transform, where image representations are scaled to a variety of differen...
Preprint
Full-text available
Multi-lingual script identification is a difficult task consisting of different language with complex backgrounds in scene text images. According to the current research scenario, deep neural networks are employed as teacher models to train a smaller student network by utilizing the teacher model's predictions. This process is known as dark knowled...
Preprint
Full-text available
Object detection in natural scenes can be a challenging task. In many real-life situations, the visible spectrum is not suitable for traditional computer vision tasks. Moving outside the visible spectrum range, such as the thermal spectrum or the near-infrared (NIR) images, is much more beneficial in low visibility conditions, NIR images are very h...
Preprint
Full-text available
With the advent of mobile and hand-held cameras, document images have found their way into almost every domain. Dewarping of these images for the removal of perspective distortions and folds is essential so that they can be understood by document recognition algorithms. For this, we propose an end-to-end CNN architecture that can produce distortion...
Chapter
We propose a writer-specific off-line writer verification procedure to improve the reliability of the verification system. It has to be a challenging task, particularly in the off-line scenario, which uses images of the scanned document, where the dynamic information is not available. In this paper, we propose a local textural based feature Histogr...
Article
Full-text available
Gait is a behavioural biometric which sometimes changes due to diseases but it is still a strong identification metric that is widely used in forensic works, state biometric preserve sectors, and medical laboratories. Gait analysis sometimes helps to identify person’s present mental state which reflects on physiological therapy for improved biologi...
Article
Full-text available
Finding local invariant patterns in handwritten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network in this work....
Chapter
One of the most challenging aspects of medical image analysis is the lack of a high quantity of annotated data. This makes it difficult for deep learning algorithms to perform well due to a lack of variations in the input space. While generative adversarial networks have shown promise in the field of synthetic data generation, but without a careful...
Article
The success of multi column region specific convolutional networks have demonstrated the importance of fixation points in images to reduce uncertainty during classification. However, suppression of non maximal activations can lead to loss of valuable information. Moreover scalar activations are only descriptive of the presence of a feature and give...
Preprint
Capturing images of documents is one of the easiest and most used methods of recording them. These images however, being captured with the help of handheld devices, often lead to undesirable distortions that are hard to remove. We propose a supervised Gated and Bifurcated Stacked U-Net module to predict a dewarping grid and create a distortion free...
Preprint
Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit feature extraction method using a multi-scale multi-column skip convolutional neural network in this work...
Preprint
In all developing and developed countries in the world, skin diseases are becoming a very frequent health problem for the humans of all age groups. Skin problems affect mental health, develop addiction to alcohol and drugs and sometimes causes social isolation. Considering the importance, we propose an automatic technique to detect three popular sk...
Article
Full-text available
Handwritten document recognition has been an active domain of research in the field of computer vision for several years since 1914 with the development of handheld scanner for reading printed texts called “optophone”. In India, which has several different scripts in one document page, identifying them is a must to automate process: document unders...
Article
Encoder decoder models with multi-scale feature concatenations have become ubiquitous for various natural scene segmentation tasks. In the current approach, a similar model with an improved mirror connection from encoders to decoder has been proposed. Three different types of mirror connections, namely, linear, parametric and convolutional, have be...
Preprint
Cytology is the branch of pathology which deals with the microscopic examination of cells for diagnosis of carcinoma or inflammatory conditions. Automation in cytology started in the early 1950s with the aim to reduce manual efforts in diagnosis of cancer. The inflush of intelligent technological units with high computational power and improved spe...
Preprint
The present work demonstrates a fast and improved technique for dewarping nonlinearly warped document images. The images are first dewarped at the page-level by estimating optimum inverse projections using curvilinear homography. The quality of the process is then estimated by evaluating a set of metrics related to the characteristics of the text l...