Structured Data Extraction Using Artificial Intelligence | Doxie.AI

about this Video

Vijay Singh, President of Doxie.AI delves into the use of artificial intelligence to identify, categorize, and extract textual data from digital image sources in government documents, library special collections, and archival materials. Artificial intelligence allows Doxie to work far beyond the limited capabilities of an OCR engine, identifying text that is out of alignment, obscured, or even handwritten, and extracting key elements to build database content that increases discovery and makes digital image collections searchable with the data points that are most meaningful to users.

Related Content

A File Format Framework for Your Digitized Collections

A File Format Framework for Your Digitized Collections

TIFFs are high-resolution images preferred for preservation. JPEGs and JPEG-2000s champion the patron’s access copy, and PDFs serve a space in between. Here’s a quick guide to the image file…

A Simple Guide to Digital Metadata

A Simple Guide to Digital Metadata

In this blog, we’ll outline some high-level aspects of digital metadata. It can be stored inside or outside of an image and consists of several different attributes; you’ve probably heard…

A Transparent Overview of Film & Negative Digitization

A Transparent Overview of Film & Negative Digitization

Resources that allow light to pass through them are called “transmissive”. This includes slides, photographic negatives, microforms, glass plates, and all manner of film: motion picture, aerial, and more. Digitizing…

Looking for Something?

Search our site below