OCR - Optical Character Recognition

arrow_back arrow_forward
Optical Character Recognition (OCR)

Our objective is to design and develop an API that will return the information printed/written in a document, pdf, or image as a usable, well formed JSON object that can be used to automate, validate, and or fasten a specific process or transaction. We used Optical Character Recognition (OCR) technology to detect embedded printed and handwritten text, and extract recognized words into machine-readable character streams.


✓ Detect embedded printed and handwritten text
✓ Extract text from PDF and images and convert it into well formed JSON data
✓ Supporting HKID Card and Vehicle Registration Document


API Development


Ping An Insurance