Bank check OCR API that reads every check, printed or handwritten

They are printed in the line of numbers at the bottom of the check, called the MICR line. On US checks, the routing number is the 9-digit number on the left, framed by special symbols, and it identifies the bank. The account number usually comes next, in the middle, and the check number is on the right (it also appears in the top-right corner). The order can vary slightly, especially on business checks. Mindee reads the MICR line and returns the routing number, account number and check number as separate fields, with no risk of mixing them up.

Employers, payroll providers and companies paying suppliers often ask for a voided check to collect bank details for direct deposit. “VOID” is written across the check so it can’t be cashed, but the MICR line stays readable. Instead of having someone retype the numbers, which often causes payment errors, Mindee extracts the routing and account numbers, as well as the account holder’s name and the bank name, directly from a photo or scan. Because US routing numbers include a check digit, their format can also be validated automatically before the first payment.

With mobile deposit, the customer takes a photo of the front and back of the check in their banking app, after signing the back and often writing “For mobile deposit only” with the bank name. The app then reads the check and sends the deposit for processing. Mindee extracts the key data from the image: the amount in figures and in words, the payee, the date, the MICR line and the check number. Banks, fintechs and payment apps can then automatically prefill the deposit, compare the two amounts, and ask the customer to retake the photo when a field is unclear.

Mindee is not a forensic fraud detection tool, but structured data makes several key checks easy to automate. You can flag checks where the amount in figures doesn’t match the amount in words, where the payee name doesn’t match the account holder, where the date is in the future or more than six months old, and where the same check number from the same account has already been deposited, through a mobile app or in a branch. Checks that pass these controls are processed faster, and suspicious ones are sent for review before the funds are released.

Yes, your data is highly secured and protected during the entire conversion process. As an enterprise-grade OCR solution, Mindee takes data privacy very seriously. Here are the key security measures in place:

• Certified compliance: Mindee's infrastructure is SOC 2 Type II certified and fully GDPR compliant, ensuring strict industry standards for data protection.
• Encryption: All documents and extracted data are fully encrypted both in transit (during the API call) and at rest.
• Data localization: You have control over where your data is processed, with the option to host and process your data on either EU or US servers.
• Strict privacy: Mindee respects data confidentiality. Your processed documents are not shared with third parties, and your private data is not used to train global AI models.

In short, your sensitive documents are processed in a secure, isolated environment and remain completely under your control.

We provide a 14 days free trial so you can fully test any of our OCR models — no credit card required. After this, we offer different pricing tiers depending of the volume of pages processed and the features you might need. See the pricing page for more information.

The supported document formats are:

• PDF (application/pdf) – While technically a document format rather than an image, it is natively supported for all extraction models.
• JPEG / JPG (image/jpeg)
• PNG (image/png) – Must be non-animated.
• WebP (image/webp)
• TIFF / TIF (image/tiff) – Both single-page and multi-page TIFFs are supported and processed similarly to PDFs.
• HEIC (image/heic) – Apple's High-Efficiency Image Container format.

‍

📌 Important technical limitations to keep in mind:

To ensure the OCR pipeline runs smoothly and successfully returns your JSON, make sure your files adhere to the following constraints:

• Maximum file size: 100 MB per file.
• Maximum page count: Up to 200 pages per document.
• File state: The files cannot be encrypted, and PDFs must not be password-protected.