Detecting Student engagement level in classroom using AI
Class size and student-to-teacher ratio are the two most important factors determining the quality of teaching and learning in a classroom setting. In southern Asian countries, especially India, the batch sizes are substantially large, leading to a very high student-to-teacher ratio of approximately 60:1. While the government plans to improve the availability of teachers via various policy measures, technological support to the existing teaching community is much needed in helping them raise the standards of education in India.
Determining engagement levels of students is extremely complex. However, during the research, I found there is a co-relation between emotions expressed by students and the corresponding engagement level. Using the Facial Emotion Recognition algorithm, I determined the engagement level with a goal to give feedback to students and teachers, thereby improving the quality of education
Detecting Scratches on car using Computer Vision
During the pandemic, I accompanied my mother to a car maintenance garage. Observing the laborious process of manual inspection to uncover damages on the car, I was motivated to expedite the evaluation and reduce human intervention.
I began building my scratch detection app. For the app to work, images of the car's body are captured from various angles—front, back, and sides. These images are then fed into a neural network that scrutinizes them for any signs of scratches or dents.
Future Collision Collider (FCC)
Just started working with Dr Christoph Paus on the FCC project.