Bank credit card OCR (Scan To Pay)

World's fastest and most accurate (99.8% F-score) credit card Scan To Pay implementation using deep learning.

Our implementation uses DeepLayout Analysis to detect and recognize every field from the card (Number, Holder's name, Validity, Company...).
It works with all cards (credit, debit, travel, prepaid, corporate...) from all payment networks (Visa, MasterCard, American Express, RuPay, Discover...).
Both Embossed and UnEmbossed formats are supported.

Unlike other implementations we're not doing brute force OCR (trying multiple images/parameters until match). You only need a single image to get a result. There is no template matching which means the data could be malformed or at any position and you'll still have the correct result (WYSIWYG).
The number of use cases in FinTech industry are countless: Scan To Pay, Helping visually impaired users, Online shopping speed-up, payment forms auto-filling, better user experience, reducing typing errors, process automation...

You can try our SDK on your own devices (Android, iOS, Raspberry Pi, Linux and Windows) using the code released on Github with full documentation hosted here. No registration, license key or internet connection is required.