Credit card number features

· There are two types of credit card numbers: embossed and printed.
· Unlike plain text, embossed credit card numbers are difficult to distinguish contrast on background.
· Many credit cards are decorated with various images in the background, making it difficult to identify the number.
· It is difficult to identify the number when the gold or silver foil coated on the embossed number is peeled off.
· Credit cards reflect light by a plastic material.
· Different credit card issuers use different standard fonts.
· There are horizontal and vertical cards.

Credit card number recognition technology

· According to the above features, it cannot be recognized with a general text character recognition
(OCR) technology, or a number recognition technology applied with deep learning technology.

Provide deep network of the optimal credit card recognition

· Using deep learning network for credit card photos in various surroundings and backgrounds
· Minimize wrong detection by applying optimal threshold
· 99% accuracy based on normal photos

Fast recognition speed

· Fast recognition speed using GPU with server version: less than 0.1 second
· GPU : Graphics Processing Unit

OS

· Windows 10 Professional 64 bit or higher
· Windows 2016/2019 Server Standard 64 bit or higher
· Linux

Server specification

CPU version
· Intel Xeon 2.3 Ghz 4-Core or higher
· Memory: 16 GB or higher
· HDD: 300 GB or higher

GPU version
· Intel Xeon 2.3 Ghz 4-Core or higher
· Memory: 16 GB or higher
· HDD: 300 GB or higher
※ GPU: At least 6 GB of NVIDIA memory

Android

Android 8.x or higher

iOS

iOS 11.x or higher