Magnetic ink character recognition (MICR) E-13B & CMC-7

Bank check information extraction/OCR from Magnetic Ink Character Recognition [MICR] (E-13B & CMC-7) using deep learning

Automating Bank account information extraction from MICR (Magnetic ink character recognition) zones on scanned bank checks/document above human-level accuracy is a very challenging task. Our implementation reaches such level of accuracy using latest deep learning techniques. We outperform both ABBYY and LEADTOOLS in terms of accuracy and speed (almost #30 times faster).
Using a single model we're able to accurately locate the MICR zones, infer the type (E-13B or CMC-7) and recognize the fields: one-shot deep model. The performance gap between us and the other companies is more important for CMC-7 format which is more challenging than E-13B.

This technology is a key component of Remote Deposit Capture applications to process bank checks sent using mobile phones or scanners. It's a must have technology for any FinTech company.

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.