Word embeddings are the bedrock for applying Deep Learning to Natural Language Processing. A comprehensive effort is required in building corpora and training word embeddings for variety of Indian languages while considering their unique morphological rules.
Interconnectivity in rural and semi-urban areas is required to understand progress of road construction and also for planning expansions. Segmenting khachcha roads from satellite imagery is remains an unsolved challenge.
A large number of manuscripts still contain locked in them direct sources of Indic heritage knowledge. Digitisation of the documents and subsequent language processing is required to preserve the knowledge contained in these manuscripts.
Credit card statements, invoices, medical test reports, resumes all have structured information that remains locked in documents. We are exploring an extensible deep learning solution to efficiently extract structured data from such documents.
Law enforcement agencies often depend on face recognition. In the absence of a representative and large database of labelled Indian faces, any deep learning solution for face recognition is not possible.
Most primary health care units and hospitals do not have the technology and manpower to store and process ECG readings. In this project, we study the application of computer vision to classify heart conditions based on printed ECG plots.