Sandeep Singh SengarUniversity of Copenhagen · Department of Computer Science
Sandeep Singh Sengar
Doctor of Philosophy
Looking for academic, industry, and research collaborations.
About
27
Publications
61,042
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
340
Citations
Citations since 2017
Introduction
Key Skills in Python, Matlab, TensorFlow, PyTorch, Machine Learning, Computer Vision, and Image/Video Processing. Currently, pursuing my PostDoc in Medical Imaging from the University of Copenhagen Denmark. Experienced and Strong education professional with a Doctor of Philosophy (Ph.D.) focused in Image and Video Processing, Computer vision from Indian Institute of Technology (Indian School of Mines), Dhanbad and an M.Tech. from Motilal Nehru National Institute of Technology, Allahabad, India.
Additional affiliations
February 2022 - present
November 2020 - October 2021
Position
- PostDoc Position
Description
- We applied Deep Learning techniques to segment the Knee MRI Images. In addition to this, some collaborative works are also finished with KAUST South Korea and Radiologists in Copenhagen University Hospital.
February 2019 - October 2020
Education
August 2014 - August 2017
Indian Institute of Technology (ISM)
Field of study
- Image and Video Processing
July 2009 - July 2011
July 2006 - July 2009
Publications
Publications (27)
Margin, in typography, is described as the space between the text content and the document edges and is often essential information for the consumer of the document, digital or physical. In the present age of digital disruption, it is customary to store and retrieve documents digitally and retrieve information automatically from the documents when...
The UNet has become the golden standard method for the segmentation of 2D medical images that any new method must be validated against. In recent years, a number of variations to the seminal UNet have been proposed with promising results in the papers introducing them. However, there is no clear consensus if any of these architectures generalize as...
Although IoT technology is advanced, wireless systems are prone to faults and attacks. The replaying information about routing in the case of multi-hop routing has led to the problem of identity deception among nodes. The devastating attacks against the routing protocols as well as harsh network conditions make the situation even worse. Although mo...
The presence of community structures in complex networks reveals meaningful insights about such networks and their constituent entities. Finding groups of related nodes based on mutual interests, common features, objectives, or interactions in a network is known as community detection. In this paper, we propose a novel Stacked Autoencoder-based dee...
The limited dynamic range of commercial compact camera sensors results in an inaccurate representation of scenes with varying illumination conditions, adversely affecting image quality and subsequently limiting the performance of underlying image processing algorithms. Current state-of-the-art (SoTA) convolutional neural networks (CNN) are develope...
UNet has become the gold standard method for segmenting 2D medical images that any new method must be validated against. However, in recent years, several variations of the seminal UNet have been proposed with promising results. However, there is no clear consensus on the generalisability of these architectures, and UNet currently remains the metho...
Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification, etc.) by encouraging underlying algorithms to focus on multiple discriminative features. However, as these techniques destroy spatial relationship with neighboring regio...
With the swift rise of social networking sites, they have now come to hold tremendous influence in the daily lives of millions around the globe. The value of one's social media profile and its reach has soared highly. This has invited the use of fake accounts, spammers and bots to spread content favourable to those who control them. Thus, in this p...
Video surveillance is one of the widely used and most active research applications of computer vision. Although lots of works have been done in the area of smart surveillance, but still there is a need of effective compression technique for compact archival and efficient transmission of vast amount of surveillance video data. In this work, we propo...
For specific identification process, Identity Management details an ailment of supplying authorized owners with secure and easy admittance to information and solutions. For choosing the individual's identity, the primary goal is actually executing secured identification feature. PINs, keys, gain access to cards, passwords, tokens are actually the p...
Moving object detection is a fundamental task and extensively used research area in modern world computer vision applications. Background subtraction is one of the widely used and the most efficient technique for it, which generates the initial background using different statistical parameters. Due to the enormous size of the video data, the segmen...
Motion segmentation from the video datasets has several important applications like traffic monitoring, action recognition, visual object tracking, and video surveillance. The proposed technique combines the structure-texture decomposition and the improved three frames differencing for motion segmentation. First, the Osher and Vese approach is empl...
Moving object detection is a basic and important task on automated video surveillance systems, because it gives the focus of attention for further examination. Frame differencing and W4 algorithm can be individually employed to detect the moving objects. However, the detected results of the individual approach are not accurate due to foreground ape...
Detecting moving objects from video frame sequences has a lot of useful applications in computer vision. This proposed method of moving object detection first estimates the bi-directional optical flow fields between (i) the current frame and the previous frame and between (ii) the current frame and the next frame. The bi-directional optical flow fi...
Motion detection is one of the key issues in intelligent video surveillance, traffic monitoring and video-based human computer interaction. In this paper, we have efficiently detected the moving objects by computing the optical flow between three consecutive frames. The proposed method first filters out noise in individual frames using Gaussian fil...
Moving object detection is a widely used and important research topic in computer vision and video processing. Foreground aperture, ghosting and sudden illumination changes are the main problems in moving object detection. To consider the above problems, this work proposes two approaches: (i) improved three-frame difference method and (ii) combinin...
Optical flow estimation is one of the oldest and still most active research domains in computer vision. This paper proposes a novel and efficient method of moving object area detection in the video sequence employing the normalized self-adaptive optical flow. This new approach first performs smoothing on the individual frame of the video data using...
Moving-object tracking is one of the basic and hot research domains in the computer vision area. This work presents a novel and effective method to track moving objects under a static background. Proposed method first executes the pre-processing tasks to remove noise from video frames. Then, with the help of rectangular window, we select the target...
Moving-object detection is one of the basic and most
active research domains in the field of computer vision. This
paper proposes a novel and efficient approach for moving
object detection under a static background. Proposed
approach first performs pre-processing tasks to remove noise
from video frames. Secondly, it finds the difference between
the...
The enormous size of video data of natural scene and objects is a practical threat to storage, transmission. The efficient handling of video data essentially requires compression for economic utilization of storage space, access time and the available network bandwidth of the public channel. In addition, the protection of important video is of utmo...
A Mobile Ad-Hoc Network (MANET) is characterized by dynamic nature without any physical infrastructure and centralizes access point. Routing in Ad-hoc networks is a challenging due to mobility of nodes. In this paper, a detailed simulation based performance analysis has been carried out of Ad-Hoc On-Demand Distance Vector (AODV), Dynamic MANET On-D...
Mobile Ad-hoc Network is a self configurable routing protocol. Nodes in MANET can shift freely from one place to another place and each node in MANET can take action as a transmitter, receiver and router. WiMAX is a telecommunication technology standard which provides fixed and mobile Internet access. Access Server Network (ASN) in WiMAX provides t...
IEEE 802.16 WiMAX provides high data rate but limited coverage area and 3G is well established network with low data rate as comparison to WiMAX network. So if we will combine both WiMAX and 3G network then it provides ubiquitous high speed data access as well as attract wider user base. In this paper we have taken component which is used in interw...
WiMAX and LTE are the telecommunication technology standards. WiMAX and LTE both offer high data rate. Both are used to provide
VOIP, online gaming, video conferencing, streaming media services to the users. In this paper we have done numerical analysis
of WiMAX and LTE network in the form of maximum number of users supportable and minimum demand t...
Nowadays phishing attacks are increasing with burgeoning rate which is highly problematic for social and financial websites.Many
antiphishing mechanisms currently focused to verify whether a web site is genuine or not. This paper proposes a novel anti-phishing
approach based on Dynamic watermarking technique. According to this approach user will be...
Questions
Questions (29)
Nowadays, I have seen many researchers are involved in increasing their citation count. They are using various inappropriate approaches for that. However, in last they have a good number of citations. My question starts now:
Organizations judge the profile on several factors among them one is a citation. Is it really good to have a high citation count? If one person fairly wants to do research, then for him citation count will be less (because he is not doing any fraudulent activity) and his profile will be judged lower than the cheater. Here, we are talking about only citation count, therefore please don't involve other performance measure components like quality research papers and others.
Please share your views.
This question is not directly related to research. However, I need genuine reply for it. At present, I am working in reputed private engineering college and getting attractive salary and world class facilities. Many of my colleagues are leaving this institute and joining NITs and IIITs (Indian Government National Institutes) on approximately half salary than here. For that, I want to mention some pros and cons of both kinds of job. Please comment on these.
1. Security:-
Government job is more secure.
As a computer science professional (specially Machine Learning, Computer Vision, Image Processing), we have ample job opportunities in private sectors (industries, universities etc).
2. Reputation:
Government job is more reputed than private. In government job, we can make our profile more strong (we can get good M.Tech. and PhD candidates, good funding etc), but in private it will be very difficult.
2. Salary:
In government job, salary growth is limited (fixed by rules and regulation).
There is no limit for salary in private sector (for good professionals).
Please share your experience on above points for future perspective. It is very confusive to me.
Your response will be appreciated.
Projects
Project (1)
1. Compression on segmented video data
2. Segmentation on compressed video data
