Anil Singh Parihar

Delhi Technological University | Delhi College of Engineering · Department of Computer Science & Engineering

Optical flow plays a crucial role in computer vision, and with the rapid advancements of Transformer-based models in natural language processing (NLP) and various visual tasks, Transformer architectures are becoming increasingly prevalent in the field of optical flow. In recent years, Transformer-based optical flow techniques have demonstrated supe...

In hazy environments, the computer vision system may require to perform object detection. The performance of the object detection methods degrades in a hazy environment. To overcome this issue, we propose a Bi-stream feature fusion (BFF) network for object detection in a hazy environment. The BFF network consists of three modules: hybrid input, Bi-...

In the evolving domain of autonomous vehicles, the importance of decision-making cannot be overstated. Deep Reinforcement Learning (DRL) emerges as a pivotal tool in this landscape. However, existing DRL algorithms suffer from inaccurate Q-value estimation, predominantly due to system noise and function approximation errors. This coupled with real-...

This paper proposes a Fusion and Recalibration Network (FRN) for low-light image enhancement. Firstly, The proposed method generates multi-exposure images from a single image to enhance low-light images. The proposed Feature Extraction Module (FEM) extracts multi-level features from an image. The proposed method uses Feature Augmentation Module (FA...

In retinex model, images are considered as a combination of two components: illumination and reflectance. However, decomposing an image into the illumination and reflectance is an ill-posed problem. This paper presents a new approach to estimate the illumination for low-light image enhancement. This work contains three major tasks: estimation of st...

Malware classification continues to be exceedingly difficult due to the exponential growth in the number and variants of malicious files. It is crucial to classify malicious files based on their intent, activity, and threat to have a robust malware protection and post-attack recovery system in place. This paper proposes a novel deep learning-based...

Video frame interpolation is an important area in the computer vision research activities for video post-processing, surveillance, and video restoration tasks. It aims toward increasing the frame rate of a video sequence by calculating intermittent frames between consecutive input frames. This ensures extra smooth, clear motion in order to make ani...

Video summarization is a keenly intellective video compression technique to select a subset of keyframes or keyshots which are combined to represent shorter and compendious summary of the original input video without losing the contextual semantics of the same. Previous work has shown that extracting rich contextual information from the input video...

Widespread digitalization has led to almost all utilities and services thrive on an online medium. A real-time, personalized, and trend grasping recommendation system is necessary to enhance user experience and boost business on E-commerce platforms. We propose the Multi-Model Contextual Reinforcement Learning (MMCR) constituting three novel featur...

In this paper, we present a new approach for single image dehazing based on the proposed variational optimization. A hazy image captures the information about the transmission map in terms of haze and object details present in it. We propose to estimate the initial transmission map by performing the structure-aware smoothing of the hazy image. Furt...

Rapid advancements in the E-commerce sector over the last few decades have led to an imminent need for personalized, efficient and dynamic recommendation systems. To sufficiently cater to this need, we propose a novel method for generating top-k recommendations by creating an ensemble of clustering with reinforcement learning. We have incorporated...

Sketches have been employed since the ancient era of cave paintings for simple illustrations to represent real-world entities and communication. The abstract nature and varied artistic styling make automatic recognition of these drawings more challenging than other areas of image classification. Moreover, the representation of sketches as a sequenc...

Multiview video summarization plays a crucial role in abstracting essential information form multiple videos of the same location and time. In this paper, we propose a new approach for the multiview summarization. The proposed approach uses the BIRCH clustering algorithm for the first time on the initial set of frames to get rid of the static and r...

Low-light image enhancement is a challenging field in image processing. Retinex-basedmethods perform well for low-light images. However, reflectance and illumination estima-tion is an ill-posed problem. This paper presents a new framework for the simultaneousestimation of reflectance and illumination for low-light image enhancement. The algorithmes...

Rapid advancements in the E-commerce sector over the last few decades have led to an imminent need for personalised, efficient and dynamic recommendation systems. To sufficiently cater to this need, we propose a novel method for generating top-k recommendations by creating an ensemble of clustering with reinforcement learning. We have incorporated...

The existence of haze and cloud degrades the quality of the image taken by camera sensors and decreases their clarity. The degradation can majorly be seen using the transmission map, which is one of the crucial parameters of Dehazing using a single image. The estimation of the transmission map is an underlying issue, and lots of different prior are...

Abstract– For the past few decades, machines have replaced humans in several disciplines. However, machine cognition still lags behind the human capabilities. We address the machines’ ability to recognize human drawn sketches in this work. Visual representations such as sketches have long been a medium of communication for humans. For artificially...

Image Enhancement is one of the domains in computer vision with prime importance in real-life applications. Images having poor visual quality and visual defects require enhancement to capture the details in an image. This paper proposes a novel fusion-based method for image enhancement of low light images having non-uniform illumination. The method...

Sketches have been employed since the ancient era of cave paintings for simple illustrations to represent real-world entities. The abstract nature and varied artistic styling makes automatic recognition of drawings more challenging than other areas of image classification. Moreover, the representation of sketches as a sequence of strokes instead of...

div>In this paper, we proposed a new low-light image enhancement approach to overcome the above limitations. The proposed algorithm is named as Nature Preserving Lowlight Image Enhancement (NPLIE). NPLIE estimates initial illumination and performs optimal refinement. The proposed algorithm computes the reflectance component through an element...

div>In this paper, we proposed a new low-light image enhancement approach to overcome the above limitations. The proposed algorithm is named as Nature Preserving Lowlight Image Enhancement (NPLIE). NPLIE estimates initial illumination and performs optimal refinement. The proposed algorithm computes the reflectance component through an element...

In recent years, notable research has been done in the area of communication in multi-agent systems. When agents have a partial view of the environment, communication becomes essential for collaboration. We propose a Deep Q-Learning based multi-agent communication approach: Mediated Differentiable Inter-Agent Learning (M-DIAL), where messages produ...

In recent years, notable research has been done in the area of communication in multi-agent systems. When agents have a partial view of the environment, communication becomes essential for collaboration. We propose a Deep Q-Learning based multi-agent communication approach: Mediated Differentiable Inter-Agent Learning (M-DIAL), where messages produ...

In this paper, It focuses on few out of many Retinex based method for Image Enhancement. Retinex is basically a concept of capturing an image in such a way in which a human being perceives it after looking at an object at the place with the help of their retina (Human Eye) and cortex (Mind). On the basis of Retinex theory, we can say an image as a...

This paper presents contrast enhancement algorithms based on fuzzy contextual information of the images. We introduce fuzzy similarity index and fuzzy contrast factor to capture the neighborhood characteristics of a pixel. A new histogram, using fuzzy contrast factor of each pixel is developed, and termed as the fuzzy dissimilarity histogram (FDH)....

This study presents a new contrast-enhancement approach called entropy-based dynamic sub-histogram equalisation. The proposed algorithm performs a recursive division of the histogram based on the entropy of the sub-histograms. Each sub-histogram is divided recursively into two sub-histograms with equal entropy. A stopping criterion is proposed to a...

This paper presents a fuzzy system for edge detection, using smallest univalue segment assimilating nucleus (USAN) principle and bacterial foraging algorithm (BFA). The proposed algorithm fuzzifies the USAN area obtained from the original image, using a USAN area histogram-based Gaussian membership function. A parametric fuzzy intensification opera...

In this paper, feature extraction and authentication scenarios for contact-based and contact-less palmprint images are investigated. The point-based feature extraction techniques like: Scale Invariant Feature Transform (SIFT), Harris corner detector, and Histogram of Gradient (HOG) in combination to Gabor filter are experimented for contact-based a...

This paper presents an optimal fuzzy filter for Gaussian noise in color images using Bacterial Foraging Algorithm (BFA) and cosine similarity. The filter makes use of the relationship between different color components of a pixel to remove the noise from the color images. The adaptive cosine similarity between the central pixel and the neighboring...

Bio-inspired edge detection using fuzzy logic has achieved great attention in the recent years. The bacterial foraging (BF) algorithm, introduced in Passino (IEEE Control Syst Mag 22(3):52–67, 2002) is one of the powerful bio-inspired optimization algorithms. It attempts to imitate a single bacterium or groups of E. Coli bacteria. In BF algorithm,...

A novel technique is presented to detect and remove the salt and pepper noise in digital color images. The algorithm is proposed for detection of noisy pixel, edges and noise free pixels by utilizing basic property of salt and pepper noise. Each pixel is treated according whether it is edge pixel, noisy pixel or pixel from smooth region etc. Noisy...

This paper presents two fuzzy filters for the removal of both Impulse and Gaussian noise in color images. A combination of these two filters also helps in eliminating a mixture of these two noises. For dealing with the Impulse noise, an algorithm is developed to search for a set of uncorrupted pixels in the neighbourhood of the pixel of interest (i...