वेदात् सर्वं प्रसिध्यति


Text Extraction, OCR , Annotation platform

A web based platform for text extraction (via OCR) , editing, proofreading, supporting collaborative text processing workflows. Textract’s sophisticated annotation platform , unicode text searching and a rich internal object model representation allows complex use-cases for text and manuscript processing. Rich research driven workflows also enables team based approaches to text research and study. The platform also is amenable for for creating outputs for bulk typesetting and reprinting purposes.

The OCR libraries are script agnostic and custom algorithms for handwritten text in various bharatiya scripts have also been developed and feature in the Textract platform.

The software is actively used in research and academic settings. Turnkey bulk processing of legacy print documents , books and the associated text processing for use by Publishers , Libraries and others is currently being explored.

See it in action.


Dr. Ravi Kiran Sarvadevabhatla

Ravi Kiran is an Assistant Professor at the International Institute of Information Technology- Hyderabad (IIIT-H).His research interests include applied machine learning, deep learning, analytics for photos, videos and document images. Applying techniques from machine learning, computer vision to solve challenging problems related to Indic multimedia content forms a major theme of his research and drives his participation in the vedavaapi platform.

For additional info, visit webpage

Knowledge Platform

Vedavaapi’s research efforts, spanning IKS have provided valuable insights to help develop IKS primitives for use in computational settings. We are in the process of building multiple APIs , which could potentially make available query-able nuggets of knowledge which could be used in building consumer apps and other kinds of software. Knowledge from various shaastra like Ayurveda, Yoga, Vaastu and others are being curated and are being made accessible computationally.

Scholars , students and experts in shaastra use web based knowledge capture software to interact with the knowledge platform core , as part of ongoing shaastra map research in academic settings.