Debotosh Bhattacharjee

Jadavpur University | JU · Department of Computer Science and Engineering

While past research has emphasized the importance of late blight infection detection and classification, anticipating the potato late blight infection is crucial from the economic point of view as it helps to significantly reduce the production cost. Furthermore, it is necessary to minimize the exposure of potatoes to harmful chemicals and pesticid...

This paper presents a methodology for detecting unhealthy lemons in a lemon dataset based on a deep Convolutional Neural Network (CNN) and transfer learning. Initially, a CNN model was developed and trained, after which a new model was framed on the existing CNN model using transfer learning. The base model was trained to a satisfying level of accu...

Plant disease classification using machine learning in a real agricultural field environment is a difficult task. Often, an automated plant disease diagnosis method might fail to capture and interpret discriminatory information due to small variations among leaf sub-categories. Yet, modern Convolutional Neural Networks (CNNs) have achieved decent s...

This paper presents a new technique for person recognition based on the fusion of hand geometric features of both the hands without any pose restrictions. All the features are extracted from normalized left and right hand images. Fusion is applied at feature level and also at decision level. Two probability based algorithms are proposed for classif...

A finger biometric system at an unconstrained environment is presented in this paper. A technique for hand image normalization is implemented at the preprocessing stage that decomposes the main hand contour into finger-level shape representation. This normalization technique follows subtraction of transformed binary image from binary hand contour i...

This paper presents a human verification scheme in two independent stages to overcome the vulnerabilities of attacks and to enhance security. At the first stage, a hand image-based CAPTCHA (HandCAPTCHA) is tested to avert automated bot-attacks on the subsequent biometric stage. In the next stage, finger biometric verification of a legitimate user i...

Crop yield production could be enhanced for agricultural growth if various plant nutrition deficiencies, and diseases are identified and detected at early stages. Hence, continuous health monitoring of plant is very crucial for handling plant stress. The deep learning methods have proven its superior performances in the automated detection of plant...

This paper is based on the recognition of hidden objects which is embedded in colormaps generated by using special programs in terahertz video surveillance systems. Terahertz imaging is popular because of its capability to see through opaque objects. So, this imaging technique can be used in the detection of hidden objects, medical diagnosis, and m...

Image compression is a class of algorithms that reduces the storage space requirement for a digital image. Lossy image compression techniques achieve higher compression but the visual quality of the decompressed image is degraded many times. Decompressed images lose their visual appeal due to compression artifacts. These compression artifacts are i...

This study introduces a novel approach to enhance the compression ratio of the vector quantization (VQ) algorithm by specifically targeting the compression of its codebook. The VQ algorithm typically generates an index matrix and a codebook to represent compressed images. The proposed method focuses on reducing the size of the codebook, which compr...

This paper presents a methodology for detecting unhealthy lemons in a lemon dataset based on a deep Convo-lutional Neural Network (CNN) and transfer learning. Initially, a CNN model was developed and trained, after which a new model was framed on the existing CNN model using transfer learning. The base model was trained to a satisfying level of acc...

The Devanagari script originated from the ancient Brahmi script and is a widely used Indic script for writing different languages, like Sanskrit, Hindi, Marathi, Nepali, and Konkani. Recognizing handwritten Devanagari characters poses significant challenges due to their complexity and handwriting variability. This literature review examines the evo...

Automatic detection of human activity is one of the growing research areas due to the wide range of applications like elderly and patient monitoring for ambient assistive living, visual surveillance, etc. This paper presents a novel bi-channel deep learning model to recognize several human daily living activities. One channel includes activity clas...

In this study, we proposed Nuclei-Net: A multi-stage fusion model for segmenting nuclei in microscopy images. Our proposed model works in two stages. In the first stage, we incorporated a deep learning (DL)-based model namely Mask Region-Based-CNN (Mask-RCNN) for the coarse segmentation of the nuclei. However, it can be observed that the predicted...

The world has witnessed the deadly impact of the Novel Corona Virus (COVID-19), claiming millions of lives since its outbreak in early December 2019. Early virus detection plays a crucial role in controlling this highly contagious disease. Though Reverse Transcription Polymerase Chain Reaction (RT-PCR) is the current standard for confirmation of CO...

PROGRAM of the joint meeting International Scientific and Practical Conference Innovative Concepts and Technologies for Pharmaceutical and Food Industry: Finding Ways for Mutually Beneficial Cooperation” (ICTPFI-2023) and Indian-Russian Webinar under support by Department of Science & Technology (DST) Government of India and Ministry of Science &...

Automated segmentation of cervical cells is a prerequisite for detection of cervical lesions. However, this segmentation is a highly challenging task since the cervical cells are highly overlapping forming clumps, resulting in irregular cytoplasmic boundaries. Nuclei detection is very crucial for individual cell segmentation because each cell is re...

The application of depth cameras for 3D visual data based measurements (VBM) is an active research area. 3D face recognition is one such niche area that is drawing the attention of researchers. This paper introduces a new 3D facial database named JUDeiTy3DK developed by a research group at Jadavpur University, Kolkata, India, using Kinect as a visi...

The application of depth cameras for 3D visual data based measurements (VBM) is an active research area. 3D face recognition is one such niche area that is drawing the attention of researchers. This paper introduces a new 3D facial database named JUDeiTy3DK developed by a research group at Jadavpur University, Kolkata, India, using Kinect as a visi...

Accurate segmentation of colorectal polyps is crucial for the early diagnosis of Colorectal Cancer (CRC). In clinical practice, the segmented polyp provides valuable diagnostic information to decide the degree of malignancy through optical biopsy. However, precise segmentation of polyps is very challenging as the appearance and morphology of polyps...

Fine-grained image classification (FGIC) is a challenging task due to small visual differences among inter-subcategories, but large intra-class variations. In this paper, we propose a fusion approach to address FGIC by combining global texture with local patch-based information. The first pipeline extracts deep features from various fixed-size non-...

The COVID-19 pandemic had a catastrophic effect on almost every country, with a reported 6 million deaths by 2022. It is caused by an RNA virus named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). To date, there have been five variants of SARS-CoV-2, namely alpha, beta, gamma, delta, and omicron. Each of these variants can potentiall...

Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the Sports, Yoga, and Dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification task due to the complex movement of body parts. Deep Convolutional N...

Automatic analysis of colonoscopy images has been an active field of research motivated by the importance of early detection of precancerous polyps. However, detecting polyps during the live examination can be challenging due to various factors such as variation of skills and experience among the endoscopists, lack of attentiveness, and fatigue lea...

In this study, we proposed Nuclei-Net: A multi-stage fusion model for segmenting nuclei in microscopy images. Our proposed model works in two stages. In the first stage, we incorporated a deep learning (DL) based model namely Mask Region-Based-CNN (Mask-RCNN) for the coarse segmentation of the nuclei. However, it can be observed that the predicted...

The capturing and development of a real time 3D face recognition system is always a big challenge and attracts huge popularity nowadays. This is because, in most security systems employing face recognition, it is always crucial to capture live images and recognize them. This should save time and cost as well, and incredibly is acceptable across all...

The accreditation of an engineering degree is crucial since, without it, the degree awardee might not be allowed to operate as an engineer legally in most countries across the world as well as in its own. Examining an engineering degree course to see if it satisfies the criteria established by the Engineering or Technology Council is known as accre...

Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is widely used to prevent malicious automated attacks on various online services. Text- and image-CAPTCHAs have shown broader acceptability due to usability and security factors. However, recent progress in deep learning implies that text-CAPTCHAs can easily be exp...

Completely automated public turing test to tell computers and humans apart (CAPTCHA) is widely used to prevent malicious automated attacks on various online services. Text- and image-CAPTCHAs have shown broader acceptability due to usability and security factors. However, recent progress in deep learning implies that text-CAPTCHAs can easily be exp...

With the ever-increasing security threats in recent years, biometric authentication has become omnipresent. Among all biometric characteristics, face recognition research has gained traction lately. This paper proposes a new face image descriptor named Local Discrete Cosine Transform Binary Pattern (LDCTBP) for illumination- and modality-invariant...

Polyp segmentation is a crucial step for the early diagnosis of colorectal cancer. However, the heterogeneous nature of polyps poses a significant challenge in the segmentation task, and it is still an unsolved problem. So in this study, we have proposed a deep learning network, namely “a spatial attention-based residual M-Net for polyp segmentatio...

In medical image analysis, segmentation of the region-of-interest is the crucial phase for proper diagnosis. However, this task is very challenging due to missing or diffuse organ/tissue boundaries. However, deep learning frameworks based on the U-Net backbone have gained immense popularity since those can deal with image inconsistencies. This stud...

Soft biometric traits (e.g., gender, age, etc. can characterize very relevant personal information. The hand-based traits are studied for traditional/hard biometric recognition for diverse applications. However, little attention is focused to tackle soft biometrics using hand images. In this paper, human gender classification is addressed using the...

Emotion recognition plays a significant role in cognitive psychology research. However, measuring emotions is a challenging task. Thus, several approaches have been designed for facial expression recognition (FER). Although, the challenges increases further as the data transits from laboratory-controlled environment to in-the-wild circumstances....

Cancer cell segmentation is challenging since they grow in tightly packed colonies (clumps), causing adjacent cells to overlap. In this work, we proposed an automated vision-based analysis framework, 2pClPr: A 2-phase Clump Profiler for the segmentation of cancer cells in fluorescence microscopy images. In the first phase, we proposed a deep learni...

Human body-pose estimation is a complex problem in computer vision. Recent research interests have been widened specifically on the sports, yoga, and dance (SYD) postures for maintaining health conditions. The SYD pose categories are regarded as a fine-grained image classification (FGIC) task due to the complex movement of body parts. Deep convolut...

Underwater image enhancement is a challenging area in computer vision research. Underwater images suffer from poor visibility, non-uniform lighting, low contrast, blurring, noise, shadows and color shading, etc. So the visual quality of the underwater images is not good enough like image captured in open air. Therefore enhancement of these images i...

This paper is based on the analysis and recognition ofterahertz images. Terahertz imaging is now extremely populardue to its power to see through opaque objects. So, this type ofimaging can be used in the detection of hidden objects, medicaldiagnoses, and many other real-life applications. This paper hastwo significant contributions: firstly, how t...

Medical images mostly suffer from data imbalance problems, which make the disease classification task very difficult. The imbalanced distribution of the data in medical datasets happens when a proportion of a specific type of disease in a dataset appears in a small section of the entire dataset. So analyzing medical datasets with imbalanced data is...

Adaptive video monitoring settings have been extensively deployed in recent years. Smart video monitoring technology enables the acquisition and analysis of movies from various devices, as well as automatic analysis based on knowledge gathering. However, the storage capacity is restricted, and the important frames from the movie cannot be saved. Th...

This paper introduces a hybrid filter bank-based convolutional network to develop a 3D face recognition system in different orientations. The filter banks approach has been mainly used for feature representation. The hybridization in filter banks is primarily generated by a fusion of principal component analysis (PCA) and independent component anal...

For the last two decades, image processing techniques have been used frequently in computer vision applications. The most challenging task in image processing is restoring images that are degraded due to various weather conditions. Mainly, the visibility of outdoor images is corrupted due to adverse atmospheric effects. The visibility of acquired i...

MicroRNAs (miRNAs) play a key role in the regulation of gene expression. Perfect or in-perfect complementarity of binding between miRNAs and a messenger RNA (mRNA) may lead to mRNA degradation or translational inhibition. In this regard, we have explored the role of miRNA and their target mRNAs in tumorous and normal tissues of molecular breast can...

A computer-aided diagnosis (CAD) system can be helpful for the detection of malignant tumors in the breast. Ultrasound imaging is a type modality with low cost and lower health risk. In this paper, we have classified benign and malignant breast tumors from ultrasound images. We have used the image quality assessment approach for this purpose. No-re...

Breast cancer is the most common cancer(s) among women worldwide. The survival rate decreases if the cancer is not detected at an early stage. Breast ultrasound (BUS) is emerging as a popular modality for breast cancer detection owing to its several advantages over other modalities. We proposed a novel deep learning framework named BUS-Net for auto...

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...

Various weather conditions degrade images, and hence the quality of the images is compromised to a large extent. Atmospheric conditions like Rain, Fog, Haze, Mist, etc., degrade scenes, and the scene’s acquisition results in noisy images. The noisy images have less visibility than regular images. Therefore, the images degraded by the weather condit...

This chapter explores the current trend and needs for deep neural networks (DNN) processing in realtime in resource-constrained hardware like IoT and discusses the different challenges and opportunities. The chapter summarizes the latest developments in accelerating DNN. The various architectures for DNN execution that present very novel solutions...

During image processing, it is observed that the input images got distorted for various reasons. The distortion of images lowers the quality of the images, which affects the processing of the images. Therefore, assessment of the quality of an image is very much necessary before further processing it. Blurriness is the most frequent form of degradat...

This paper presents a novel approach for Human Face Recognition, namely Regularized Bi-partitioned Entropy Component Analysis (RBECA). This conservative approach regularizes the kernel entropy components by deterring the noise and affecting the lower entropy regions area, making the method robust to noise. The kernel feature space, formed by the ke...

In the field of image processing, analyzing fog-affected images is challenging, as their visibility is degraded. In the absence of state-of-the-art image processing techniques to mitigate the impact of high-density fog, an adaptive-function-based image-defogging technique is proposed in this paper. The proposed technique accurately enhances such de...

Color is very important to for the visual appeal of an image. In this study we aim to colorize human face images using Genetic Algorithm and its modified version. The face images have been considered for color conversion due to their extensive use in various important fields like archaeology, entertainment, law enforcement etc. The experiment has b...

Thyroid nodules are widespread for the age-group of above 60. All thyroid nodules do not tend malignancy. The ultrasound imaging technique is widely used to analyze the characteristic of thyroid nodules in a periodic interval. The statistic shows that the cases of carcinoma in thyroid nodules have increased in recent years. So, as a protective meas...

The human face is considered a popular biometric because of its non-intrusive acquisition procedure. There are two kinds of facial recognition, one using 2D face images and the other involving 3D face images. Various factors like pose, illumination, occlusion, and expression affecting the performance of a 2D face recognition system can be tackled r...

COronaVIrus Disease 2019 (COVID-19) emerged as a global pandemic in the last two years. Typical abnormal findings in chest computed tomography (CT) images of COVID-19 patients are ground-glass opacities (GGOs) and consolidation, which signify the extent of damage caused to the lungs. The manual annotation of these abnormalities for severity analysi...

Heterogeneous Face Recognition (HFR) is a challenging task due to the significant intra-class variation between the query and gallery images. The reason behind this vast intra-class variation is the varying image capturing sensors and the varying image representation techniques. Visual, Infrared, thermal images are the output of different sensors a...

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...

Visibility issues in intelligent transportation systems are exacerbated by bad weather conditions such as fog and haze. It has been observed from recent studies that major road accidents have occurred in the world due to low visibility and inclement weather conditions. Single image dehazing attempts to restore a haze-free image from an unconstraine...

Human Action Recognition (HAR) has achieved a remarkable milestone in the field of computer vision. Apart from its varied applications in human–computer interactions, surveillance systems and robotics, in recent times, it has extended its applicability in the fields like healthcare, multimedia retrieval, social networking, and education as well. Ov...

This paper addresses the Instrument Segmentation Task, a subtask for the “MedAI: Transparency in Medical Image Segmentation” challenge. To accomplish the subtask, our team “Med_Seg_JU” has proposed a deep learning-based framework, namely “EM-Net: An Efficient M-Net for segmentation of surgical instruments in colonoscopy frames”. The proposed framew...

This paper presents a new facial feature descriptor called Fused Cross Lattice Pattern of Phase Congruency (FCLPPC) for high accuracy homogeneous and heterogeneous illumination invariant intra/inter-modality face recognition. Using the dimensionless phase congruency features, an effective homogeneous and heterogeneous illumination invariant local f...

Recent research on biometrics focuses on achieving a high success rate of authentication and addressing the concern of various spoofing attacks. Although hand geometry recognition provides adequate security over unauthorized access, it is susceptible to presentation attack. This paper presents an anti-spoofing method toward hand biometrics. A prese...

Background: MicroRNAs (miRNAs) are a class of \(\sim \)22-nucleotide endogenous non-coding RNAs, having critical roles across various biological processes. It also performs a meaningful character in tumorigenesis. Therefore, the identification of differentially expressed miRNAs is a growing challenge. In this regard, our paper presents the approach...