IT professional with hands-on experience in Machine Learning, Computer Vision, Natural Language processing along with specialization in Big Data and IoT.
Worked on Text Summarization & Keyphrase Extraction
Worked with Ticker Symbol Data
Generated poems with Markov chains
Generated Word cloud for most used words in a poem
Worked on SIMD vectorization with Intel Xeon Phi
Worked on Parallel Programming and Optimization with Intel Architectures.
Machine Learning approach to recognize license plate from live stream videos. We have selected OpenALPR, k-NN and Convolutional Neural Networks (CNN) based techniques, adapted them for local conditions, compared their accuracy on both still images and live stream videos. Our analysis demonstrates that the CNN based approach is the most suitable for recognizing number plates in India.
View Project PublicationTeam-mate: Dilip G
A project aimed at conserving electricity used by the street lights. Almost all the street lights are turned ON throughout the mid-night even when it is rarely used, we decided to build an IOT system that manages the intensity of light based on the presence of human beings with the help of a camera.