SUDIPTA SARKAR (সুদীপ্ত সরকার)
"Education is the manifestation of the perfection already in man." - Swami Vivekananda
|| An Enthusiastic Learner || Computer Science || Deep Learning || Computer Vision ||
|| An Enthusiastic Learner || Computer Science || Deep Learning || Computer Vision ||
My name is Sudipta Sarkar (Rik), a strong follower of Swami Vivekananda, Thakur Shree Ramakrishna and Holi Ma Sharada. Currently, I am pursuing my master's degree in Ramakrishna Mission Residential College (Autonomous), Narendrapur and I completed my bachelor's degree in Computer Science (Hons.) from Ramakrishna Mission Vivekananda Centenary College, Rahara,
During my five years of undergraduate and postgraduate studies, I had the opportunity to visit more than three Ramakrishna Mission Centers. I deeply admire their philosophy, work, and spiritual ideologies. Throughout this period, I met many potential friends, teachers, and monks who have continuously encouraged me to be a diligent learner and, more importantly, a good human being. I am truly grateful to all my friends, teachers, family members, and especially to the monks, whose guidance has played a crucial role in shaping me into a better person. Today, I strive not only to excel in the field of computing but also to grow spiritually and become a better individual in every aspect of life.
The name "Sudipta" (সুদীপ্ত) is of Sanskrit origin and is commonly used in Bengali-speaking regions. It is a combination of two Sanskrit words: "Su" meaning "good," "auspicious," or "prosperous". "Dipta" meaning "bright," "shining," or "illuminated". So, the meaning of Sudipta is often interpreted as "one who is brightly shining"(যে আলোকিতভাবে উজ্জ্বল) or "the one who is prosperous and enlightened."(যে সমৃদ্ধ ও জ্ঞানী) It conveys the idea of someone who is radiant, intellectually bright, or blessed with success.
Rearranged video frames into super images to convert video action recognition into an image classification task. Employed Hiera Vision Transformer (Hiera-ViT) as the classifier, achieving competitive results on Kinetics-400 and Something-Something V2 (SSV2) datasets.
Tools: PyTorch, Video Action Recognition, Activity Detection
Project Link:
Supervisor: Dr. Abir Das, Assistant Professor, IIT Kharagpur
This project focuses on improving message hiding techniques using Steganography and applying Steganalysis to detect hidden signals. The goal is to maximize PSNR and NCC values using optimizers like PSO and apply CNNs and LSTMs for Steganalysis.
Tools: Python, Steganography, Deep Learning, CNN, LSTM
Project Link:
Supervisors: Dr. Siddhartha Banerjee & Bibek Ranjan Ghosh, Associate Professors, Ramakrishna Mission Residential College
The project aims to detect key human emotions like anger, disgust, fear, happiness, sadness, surprise, and neutrality using Convolutional Neural Networks (CNN). The model achieves 61.25% validation accuracy after 42 epochs.
Tools: Python, Deep Learning, CNN
Project Link: Show Project
Supervised by: Prasenjit Das, Assistant Professor & Dr. Chayan Halder, Assistant Professor, Ramakrishna Mission Vivekananda Centenary College
Cell nuclei segmentation is a vital task in microscopy image analysis for biological studies. This project explores developing accurate segmentation algorithms that can run on resource-constrained computing environments.
Tools: Python, Deep Learning, UNet
Project Link: Show Project
Supervised by: Dr. Biswajit Biswas, Assistant Professor, Ramakrishna Mission Vivekananda Centenary College
This project classifies potato leaf diseases using deep learning techniques to improve early detection and successful crop cultivation in agriculture.
Tools: Python, Deep Learning, CNN
Project Link: Show Project
This Virtual Assistant mimics popular systems like Amazon Alexa or Siri using the OpenAI API, Python, and various libraries to create voice-interactive features.
Tools: Python, OpenAI API, pyttsx3, speech_recognition, webbrowser
Project Link: Show Project
This is a CLI-based game written in C++ where players race to reach a target number. The game uses backtracking algorithms and is designed so that the machine always wins if it selects first.
Tools: C++
Project Link: Show Project
Contributing to an open-source collection of data structure and algorithm implementations as per UGC syllabus for B.Sc. Computer Science students.
Tools: C++, Data Structures & Algorithms
Project Link: Show Project
A CLI-based medical store billing management system software developed in C++ during the first semester of my studies.
Tools: C++
Project Link: Show Project
Feel free to reach out to me: