Saumik Bhattacharya

Bio: Saumik Bhattacharya is an academic researcher from Indian Institute of Technology Kharagpur. The author has contributed to research in topics: Computer science & Video denoising. The author has an hindex of 10, co-authored 48 publications receiving 248 citations. Previous affiliations of Saumik Bhattacharya include Indian Institute of Technology Kanpur & Indian Institute of Technology Roorkee.

Effects of Degradations on Deep Neural Network Architectures.

Abstract: Recently, image classification methods based on capsules (groups of neurons) and a novel dynamic routing protocol are proposed. The methods show promising performances than the state-of-the-art CNN-based models in some of the existing datasets. However, the behavior of capsule-based models and CNN-based models are largely unknown in presence of noise. So it is important to study the performance of these models under various noises. In this paper, we demonstrate the effect of image degradations on deep neural network architectures for image classification task. We select six widely used CNN architectures to analyse their performances for image classification task on datasets of various distortions. Our work has three main contributions: 1) we observe the effects of degradations on different CNN models; 2) accordingly, we propose a network setup that can enhance the robustness of any CNN architecture for certain degradations, and 3) we propose a new capsule network that achieves high recognition accuracy. To the best of our knowledge, this is the first study on the performance of CapsuleNet (CapsNet) and other state-of-the-art CNN architectures under different types of image degradations. Also, our datasets and source code are available publicly to the researchers.

Viral marketing on social networks: An epidemiological perspective

Abstract: Omnipresent online social media nowadays has a constantly growing influence on business, politics, and society. Understanding these newer mechanisms of information diffusion is very important for deciding campaign policies. Due to free interaction among a large number of members, information diffusion on social media has various characteristics similar to an epidemic. In this paper, we propose and analyze a mathematical model to understand the phenomena of digital marketing with an epidemiological approach considering some realistic interactions in a social network. We apply mean-field approach as well as network analysis to investigate the phenomenon for both homogeneous and heterogeneous models, and study the diffusion dynamics as well as equilibrium states for both the cases. We explore the parameter space and design strategies to run an advertisement campaign with substantial efficiency. Moreover, we observe the phenomena of bistability, following which we estimate the necessary conditions to make a campaign more sustainable while ensuring its viral spread.

A data-driven understanding of COVID-19 dynamics using sequential genetic algorithm based probabilistic cellular automata

Abstract: COVID-19 pandemic is severely impacting the lives of billions across the globe. Even after taking massive protective measures like nation-wide lockdowns, discontinuation of international flight services, rigorous testing etc., the infection spreading is still growing steadily, causing thousands of deaths and serious socio-economic crisis. Thus, the identification of the major factors of this infection spreading dynamics is becoming crucial to minimize impact and lifetime of COVID-19 and any future pandemic. In this work, a probabilistic cellular automata based method has been employed to model the infection dynamics for a significant number of different countries. This study proposes that for an accurate data-driven modelling of this infection spread, cellular automata provides an excellent platform, with a sequential genetic algorithm for efficiently estimating the parameters of the dynamics. To the best of our knowledge, this is the first attempt to understand and interpret COVID-19 data using optimized cellular automata, through genetic algorithm. It has been demonstrated that the proposed methodology can be flexible and robust at the same time, and can be used to model the daily active cases, total number of infected people and total death cases through systematic parameter estimation. Elaborate analyses for COVID-19 statistics of forty countries from different continents have been performed, with markedly divergent time evolution of the infection spreading because of demographic and socioeconomic factors. The substantial predictive power of this model has been established with conclusions on the key players in this pandemic dynamics.

STEFANN: Scene Text Editor Using Font Adaptive Neural Network

Abstract: Textual information in a captured scene plays an important role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our knowledge, there is no significant prior work that aims to modify the textual information in an image. The ability to edit text directly on images has several advantages including error correction, text restoration and image reusability. In this paper, we propose a method to modify text in an image at character-level. We approach the problem in two stages. At first, the unobserved character (target) is generated from an observed character (source) being modified. We propose two different neural network architectures - (a) FANnet to achieve structural consistency with source font and (b) Colornet to preserve source color. Next, we replace the source character with the generated character maintaining both geometric and visual consistency with neighboring characters. Our method works as a unified platform for modifying text in images. We present the effectiveness of our method on COCO-Text and ICDAR datasets both qualitatively and quantitatively.

Localized image enhancement

Abstract: Image enhancement is a well established field in image processing. The main objective of image enhancement is to increase the perceptual information contained in an image for better representation using some intermediate steps, like, contrast enhancement, debluring, denoising etc. Among them, contrast enhancement is especially important as human eyes are more sensitive to luminance than the chrominance components of an image. Most of the contrast enhancement algorithms proposed till now are global methods. The major drawback of this global approach is that in practical scenarios, the contrast of an image does not deteriorate uniformly and the outputs of the enhancement techniques reach saturation at proper contrast points. That leads to information loss. In fact, to the best of our knowledge, no non-reference perceptual measure of image quality has yet been proposed to measure localized enhancement. We propose a fast algorithm to increase the contrast of an image locally using singular value decomposition (SVD) approach and attempt to define some parameters which can give clues related to the progress of the enhancement process.

A review on genetic algorithm: past, present, and future

Abstract: In this paper, the analysis of recent advances in genetic algorithms is discussed. The genetic algorithms of great interest in research community are selected for analysis. This review will help the new and demanding researchers to provide the wider vision of genetic algorithms. The well-known algorithms and their implementation are presented with their pros and cons. The genetic operators and their usages are discussed with the aim of facilitating new researchers. The different research domains involved in genetic algorithms are covered. The future research directions in the area of genetic operators, fitness function and hybrid algorithms are discussed. This structured review will be helpful for research and graduate teaching.

Toward Causal Representation Learning

Abstract: The two fields of machine learning and graphical causality arose and are developed separately. However, there is, now, cross-pollination and increasing interest in both fields to benefit from the advances of the other. In this article, we review fundamental concepts of causal inference and relate them to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research. This also applies in the opposite direction: we note that most work in causality starts from the premise that the causal variables are given. A central problem for AI and causality is, thus, causal representation learning, that is, the discovery of high-level causal variables from low-level observations. Finally, we delineate some implications of causality for machine learning and propose key research areas at the intersection of both communities.

Shifting More Attention to Video Salient Object Detection

Abstract: The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset representative of real dynamic scenes with high-quality annotations. To address this issue, we elaborately collected a visual-attention-consistent Densely Annotated VSOD (DAVSOD) dataset, which contains 226 videos with 23,938 frames that cover diverse realistic-scenes, objects, instances and motions. With corresponding real human eye-fixation data, we obtain precise ground-truths. This is the first work that explicitly emphasizes the challenge of saliency shift, i.e., the video salient object(s) may dynamically change. To further contribute the community a complete benchmark, we systematically assess 17 representative VSOD algorithms over seven existing VSOD datasets and our DAVSOD with totally ~84K frames (largest-scale). Utilizing three famous metrics, we then present a comprehensive and insightful performance analysis. Furthermore, we propose a baseline model. It is equipped with a saliency shift- aware convLSTM, which can efficiently capture video saliency dynamics through learning human attention-shift behavior. Extensive experiments open up promising future directions for model development and comparison.

Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future.

Abstract: Convolutional neural networks (CNNs) were inspired by early findings in the study of biological vision. They have since become successful tools in computer vision and state-of-the-art models of both neural activity and behavior on visual tasks. This review highlights what, in the context of CNNs, it means to be a good model in computational neuroscience and the various ways models can provide insight. Specifically, it covers the origins of CNNs and the methods by which we validate them as models of biological vision. It then goes on to elaborate on what we can learn about biological vision by understanding and experimenting on CNNs and discusses emerging opportunities for the use of CNNs in vision research beyond basic object recognition.

Handbook Of Image And Video Processing

Abstract: Thank you very much for reading handbook of image and video processing. As you may know, people have search numerous times for their favorite novels like this handbook of image and video processing, but end up in infectious downloads. Rather than reading a good book with a cup of coffee in the afternoon, instead they cope with some harmful bugs inside their laptop. handbook of image and video processing is available in our book collection an online access to it is set as public so you can download it instantly. Our digital library hosts in multiple locations, allowing you to get the most less latency time to download any of our books like this one. Kindly say, the handbook of image and video processing is universally compatible with any devices to read.