My current interest is in the intersection of Signal Processing with Deep learning and Computer vision.

SPAI Group's Vision: As a young citizen of India, armed with technology, knowledge and love for my nation, I realize, small aim is a crime. -- A P J Abdul Kalam, People's President AND Science is a collaborative effort. The combined results of several people working together is often much more effective than could be that of an individual scientist working alone. -- John Bardeen, Nobel Prize in both 1956 and 1972.

Masters

1. Johaan George (B-Tech, Naval Engineering, Joined - Jan 2024)

2. Amara Datta (MSc, Mathematics and Computing, Joined - Aug 2023)
   Mid-Sem Report / Mid-Sem Slides [Chanakya Fellowship Award 2024], Incoming Senior Data Scientist, MakeMyTrip.

Interns

1. Shamik Bhattacharjee (IIT Kharagpur, Joined - Feb 2024)

2. Swaralipi Datta (IIT Kharagpur, Joined - Feb 2024)

3. Anushree Ghosh (IIT Kharagpur, Joined - Feb 2024)

4. Bibhabasu Debnath (IIT Kharagpur, Joined - Feb 2024)

I am actively looking for PhD and Masters (MS/MTP) students to work with me. Self motivated, Ambitious and Keen students with a research aptitude towards signal processing, image processing, computer vision, and applied mathematics are welcome to join our SPAI group. We closely follow this philosophy: please read this. If you are interested, please apply through the IIT Kharagpur PG admissions process, specifying Centre of Excellence in Artificial Intelligence among your preferred departments/centres and listing me as a potential supervisor.

Regarding internships, I see it as an integration of classroom knowledge and theory (studied in the first few years in UG) with practical application and skills (gained doing intership). For the same reason, sorry that I may not be able to entertain first/second year UG students.

The prospective students are encouraged to visit my group for two weeks to get a good understanding about my group, our working style, and to make an optimal decision based on bilateral matching.

LoR policy: Truth be told, my letter of reccommendation does not have much value; so your depth and breadth of research should reflect your ambition!

A systematic analysis of computer vision applications specific to commercial pig management.

Motion deblurring for IR cameras mounted on a high steering-rate gimbal system (processed in real time).

A Deep Learning approach for motion deblurring for dual-lens cameras to address incoherent views, ill-posedness, and adaptive scale.

Motion deblurring for Rolling shutter cameras, Light field cameras, and Unconstrained Dual-lens cameras.

Motion deblurring for dual-lens cameras possess an ill-posedness, which calls for a prior for depth-consistent deblurring.

Full-resolution light field deblurring can be divided into independent subtasks, wherein a single task reinforces other tasks.

A method for the scenario of a fast moving camera wherein rolling shutter distortions results in intra-frame occlusions.

How can we bridge today's ubiquitous rolling shutter cameras with the well-studied conventional cameras, pertaining to motion deblurring?

Deep Learning is used to obtain the attributes of object motion and camera motion, which is then employed for segmenting moving object(s).

A fully-automatic denoising based on a convex prior on SEM images, which eradicate (difficult to infer or possibly erroneous) noise models.

Wavelet thresholding (Visushrink) is extended to Contourlet transform, in order to enhance the performance of bilateral and NLM filtering.

Copyright notice: Copies of the papers are provided here for convenient dissemination of scholarly work. They can be downloaded for non-commercial research and education purposes only. Copyrights of the papers usually belong to the publishers of the journals or proceedings and must be adhered to by anyone using these materials. For other materials, feel free to use it at your convenience for good deeds! ™