Santosh kumar PandaNational Institute of Technology Rourkela | NITR · Department of Computer Science and Engineering (CS)
Santosh kumar Panda
Doctor of Philosophy
About
3
Publications
1,740
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
5
Citations
Introduction
I hold a master's degree in computer science and applications from Sambalpur University, where I was the university Gold Medalist. I further pursued M.Phil in image processing and was honored with the DST INSPIRE fellowship by the Government of India. I am pursuing my Ph.D. in image processing and computer vision at NIT Rourkela.
Education
August 2018 - January 2020
June 2016 - June 2018
Publications
Publications (3)
Digital camera sensors may struggle to capture images in low-light environments, resulting in lower brightness and contrast levels, color degradation, undesirable characteristics, and noise. Such reduced-quality images adversely affect the performance of computer vision algorithms. With the advancement in deep neural networks, many methods have eme...
The modified BFGS optimization algorithm is generally used when the objective function is non-convex. In this method, one has to move in a specific direction such that the value of the objective function reduces. Therefore, the different inexact line search or exact line search plays an important role in optimization. Here, we have studied Modified...
Bag of Features or BoF approach has been used in many computer vision tasks, including image classification, video search, robot localization, and texture recognition. It is so widely popular because of its simplicity. These methods are based on unordered collections of image descriptors which are then quantized and are discarded spatial informatio...
Questions
Questions (4)
Any Upcoming call for papers in journals (SCI/SCIE indexed) related to image processing or computer vision.
Special issues related to my area, whose submission dates are within a few months.
Suppose, for example, I have two domains of dataset X and Y, and obviously, they are not paired. I want to train it for an image translation task to get a model to infer an image and translate it from domain X to Y.
I know GANs are heavily used for such tasks, but can other core methods or algorithms do that?
I have a model, where in some part of which I have used 3 convolutional layers each having 3*3 kernel size parallelly like this
(in_) # My InstantiateModel
x1 = Conv2D(32, 3, padding="same")(in_)
x2 = Conv2D(32, 3, padding="same")(in_)
x3 = Conv2D(32, 3, padding="same")(in_)
So basically a 3*3 kernel is a 3*3 matrix, so I want to know what are the values of those kernels/matrix. In a convolutional layer we are directly specifying the size of kernel like above, where 3 is the kernel size , but what are the values of those kernel ?
For my case where I am using 3 layers with same kernel size parallelly, so are the values of each kernel same for each layer or different. Please provide me some information on this thing.
There are many game theory algorithms , and many of them are used in the field of image processing. But how can it be used for image enhancement. And which algorithm will be more suitable for this job.
