Home

Welcome to my page.

I design and implement computer vision systems. My interests are in applying machine learning to computer vision, 3D mapping/tracking and robotic perception.

I work at Trifo Inc. where we develop robotics for home.

https://www.linkedin.com/in/prsnkrsn

Drop me an email at: krishnasamy <dot> prasanna <at> gmail <dot> com

Past Experience

At Apple, I implemented event detection algorithms on images. I also performed a lot of analyses on the time series' and implemented 3D algorithms on pointclouds.

At Arraiy. I worked on making visual content creation easier for artists using the latest in computer vision and deep learning. I worked on solutions for matting foregrounds using deep learning and geometry. Arraiy was acquired by Matterport.

I worked for Magicleap Inc. as a computer vision engineer which was a whole lot of fun. There I worked on hand recognition, deep learning for gestures, depth cameras, object tracking, multiple camera pose and calibration. These were features that enabled mixed-reality experiences.

Prior to that, I was at Amazon Lab126 on their emerging technologies team. Here I worked on object tracking, machine learning for gesture recognition, and 3D plane finding.

My graduate school work was under Prof. David Kriegman and Prof. Serge Belongie on modeling distorted fingerprints and increasing the accuracy of systems for them.

Education

I earned a Masters at the Dept. of Electrical and Computer Engineering in UC San Diego. During that time, I worked in the computer vision lab in UC San Diego. Prior to that, I had completed my undergraduate degree - B.E.(hons.) Electronics and Instrumentation- from BITS-Pilani, India.

Publication

Krishnasamy P., Belongie S., Kriegman D., "Wet Fingerprint Recognition: Challenges and Opportunities", International Joint Conference on Biometrics (IJCB), Washington, DC, October, 2011 -- DOWNLOAD PDF