vision

Generative Multimodal Learning for Reconstructing Missing Modality

Training a latent variable based variational inference model on multimodal data in order to perform inference with all possible combinations of missing modalities.

Highlighter(Auto field detection)

A tool to highlight/extract specific form fields from documents using classical Computer Vision and heuristics

Histopathology

A detailed literature survey of applications and relevance of Deep Learning in Histopathology

Generative Adversarial Networks: Reproducibility Study

A reproducibility test, ablation studies and extension of the seminal Generative Adversarial Networks paper

Image Stitching (Panorama)

Implemented an image stitching algorithm for creating panoramas from successive images from a rotating camera from scratch.

Modified MNIST [Kaggle]

Identifying the highest number present in modified MNIST images containing multiple handwritten digits on random backgrounds using deep learning

SIFT

Implementing Scale Invariant Feature Transform from scratch and feature matching

Image Quality Assessment

An ensemble model to quantify image quality to filter poor quality images at the client end to prevent redundant processing

Dory OCR

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

Sign Language Classification [Bachelor Project]

Deep Learning based Indian Sign Language detection for conversion to speech, a subsystem of the Hindi speech-Indian sign language interconversion system