Computer Vision

Computer vision is a discipline that studies how to reconstruct, interpret and understand a 3D scene from its 2D images in terms of the properties of the structures present in the scene. Basically, it addresses an inverse problem, i.e., to describe the world that we see in one or more images. The applications of computer vision include optical character recognition, machine inspection, 3d model building, medical imaging, automotive safety, motion capture, surveillance, fingerprint recognition and biometrics.:

Completed Projects on Computer Vision:

  1. Development of l1-magic library in C for recovery of sparse signals via convex programming
  2. Facial landmark detection system
  3. Abnormality event detection in videos
  4. Identification of temporal recurrent patterns in videos

Ongoing Projects:

  1. Nonchronological Video Synopsis and Indexing