Md Rahat-uz Zaman

PhD Student

Office: 721

Interest:

Biography

During my undergraduate thesis, I worked with Professor Dr. Md. Aminul Haque Akhand in detecting the weakness of Convolutional Neural Network (CNN) when recognizing Handwritten Numerals. I developed a methodology to overcome the weaknesses of CNNs with a new measure, the Start-End Writing Measure (SEWM), which takes into account the starting and ending points of a stroke in handwritten digits. 

After a research internship in computer vision at Ultra-X Asia Pacific, Japan, I've enrolled in the Ph.D. program at the University of Arizona. Right now, being a first-year Ph.D. student, I am working under the supervision of Professor Stephen Kobourov in the Humans, Data, and Computers (HDC) lab. I am currently trying to develop an algorithm that will take several images of an object from different perspectives, and reconstruct a 3D point embedding of that object

​​​​​Research Interests

My research interest is in the field of Deep Learning and Computer Vision. Currently, I am interested in applying Generative Adversarial Networks on 3D reconstruction from multiple images. Later in my Ph.D., I might pivot from the current objective and work on Data Visualization and Computer Vision with Deep Learning. 

What long-term project do you want to work on?

 

What do you enjoy most about your work?

I love problem-solving and developing new techniques with optimized algorithms. I enjoy closely working with different domain experts, sharing ideas, and learning from them.

What are your career goals?

My career goal is to lead quality research work either in industry or academia, where I would have the opportunity to make usable, effective technology with a positive social influence.

​​​​Tell us something interesting about yourself!

I have played almost all PC games out there. But now it is getting harder for me to even complete a single game during my Ph.D. I like to watch TV series, Anime, sci-fi, and superhero movies. I like to play badminton. I also eat a lot.