Leveraging OCR. Delivering never-before business efficiencies.
Scanned and non-digitized documents still make up a large part of business operation in traditional companies, which leads to difficulty in managing, searching, and making proper use of critical information at key decision points.
Created an easily searchable database for 13,000 certificates of construction documents by digitizing PDF images in batch by extracting and indexing them for fast search and document retrieval.
- Converted large volume of PDF data into meaningful information that can be mined for insights.
- A easy-to-store and search database to provide insights that can be found at the time of need.
Scope of Engagement
Content Management Mirco Solution
Java, Azure Computer Vision API, Elastic Search