Deep Learning

An unconditional generative model to augment medical image datasets using a single natural image.

A smart application to control the cursor based on the eye-gaze direction of a subject in a video-feed using OpenVINO toolkit. Leverages image processing and pre-trained OpenVINO-models to deliver real-time results.

OpenVINO-based Person detection and monitoring app to detect people in a designated area and deliver statistics based on the same.

Intelligent Digital Inline Holographic Micrograph (DIHM) Cell-Enhancement and Characterization Project Intro Developing a novel and efficient neural model for detecting and classifying cells such as RBC, WBC, and cancer cells, etc.

Cell-line segmentation from DIH micrograph. Signal enhancement using CNN-based Autoencoder. Cell-line characterization using CNNs. Easy accommodation of newer cell-lines using transfer learning.