A reproducibility test, ablation studies and extension of the seminal Generative Adversarial Networks paper
Implemented an image stitching algorithm for creating panoramas from successive images from a rotating camera from scratch.
Identifying the highest number present in modified MNIST images containing multiple handwritten digits on random backgrounds using deep learning
Implementing Scale Invariant Feature Transform from scratch and feature matching
An ensemble model to quantify image quality to filter poor quality images at the client end to prevent redundant processing
We created a state of the art Optical Character Recognition Engine specifically for Indian ID cards using a pipeline for document layout detection, foreground extraction, text detection, recognition and postprocessing
Deep Learning based Indian Sign Language detection for conversion to speech, a subsystem of the Hindi speech-Indian sign language interconversion system
Regression based deep learning models for automatically cropping document as foreground extraction(segmentation) task
Using traditional computer vision with deep learning algorithms for Anomalous activity detection from CCTV camera feed
Optical Character Recognition in Lecture Videos for the enrichment of Automatic Speech Recognition(ASR) system