Auto-cropping document API, tailored for multi‑page on a single file

Efficient one-tap digitization for multiple items captured in a single scan or photo

Ensure individual record precision by automatically isolating and cropping distinct documents into standalone files

Try it for free

4.8/5  (30+ reviews)

Trusted by top-tier teams worldwide

v2-Carlabella
v2-Spendesk
v2 Payfit
v2 Lucca
v2 Circula
v2-Carlabella
v2-Spendesk
v2 Payfit
v2 Lucca
v2 Circula

Without

Auto-crop

Generalist LLMs struggle with precise spatial coordinates, leading to messy crops and hallucinated document borders

Often "hallucinates" coordinates, cutting off text or logos

High-res images needed for cropping burn through tokens

Struggles with "cluttered” layout

Difficult to admit when it's "unsure" of a type

With

Auto-crop

+99%

Accurate cropping

Identifies exact physical edges

Fixed processing cost regardless of image complexity

Easily isolates 10+ items on a single scan

Built-in metrics to trigger human review only when needed

Implement “Crop” into your document workflow, in seconds

Available for every plan

From Mindee’s platform, create a new pre‑processing model by clicking on “Crop” utility

You will find it at the bottom of the user interface. If you are more familiar with this type of pre-processing model, you can directly use it by checking the Documentation for more details.

User interface displaying document types like Resume, Invoice, Receipt, and tools such as Crop, Split, and OCR for document processing.
Interface for configuring document classes with options for RECIEPT and OTHER, and buttons to Cancel or Create Utility.

Custom to your needs

Enter the document types that you may find in your files

Before final pre-processing, you need to define appropriate categories. Be sure to manually add an “Undefined” category. If a file doesn’t match to your document main categories, it will be available in the “Undefined” one.

PDF, HEIC, PNG, JPEG... MUltiple formats

Upload any document without friction : universal PDF and image support

Accelerate ingestion with native support for PDFs and all image formats. From high-res scans to mobile captures, Mindee API handles any input, ensuring your data is always ready for extraction.

Screenshot of a software interface displaying multiple cropped images of receipts with labels such as RECEIPT and OTHER and a JSON response showing metadata about detected receipts.

full document processing stack

Find all your documents cropped and individualized in standard JSON format, with corresponding bounding boxes

Pre-processing via auto-crop can then be combined with other Mindee API utilities to further improve the granularity of the extracted data.

Use auto-crop and more to optimize your document workflow

1

Capture

2

Pre-processing

3

Data extraction

4

Enrichment

5

Validation

Top view of a coffee cup, pen, manila folder with envelopes and sticky notes, and IRS tax forms on a dark surface.

Smart capture image from poor quality phone pictures, handwritten notes to native PDFs

Bridge the gap between noisy inputs and structured data. Mindee API cleans low-quality phone captures, analyse handwriting, and isolate multi-documents on a single page/picture.

Older man with gray hair and beard reviewing a large stack of papers at a desk under red text that reads 'X TIME-CONSUMING'.

AI-powered classification that identifies document "DNA" (Invoices vs. Contracts) and automates batch splitting

Manual document sorting is a bottleneck of the past. Our routing engine acts as a digital architect, instantly classifying documents and directing them to the correct business logic.

User interface showing extracted fields from a supplier document including supplier logo, name Joanna Binet, line items with quantity 2 and unit price 400, and SWIFT code 1293290221079 with confidence levels.

Extract data from any layout with outstanding accuracy : complex tables, key-value pairs, and handwritten annotations supported

Move beyond simple character recognition. Our extraction layer leverages Neural Networks to understand your data contextually, turning static unstructured files into dynamic, structured assets in standard JSON format.

Logos of software platforms Sage, Salesforce, Odoo, Oracle, Sellsy, HubSpot, SAP, and Microsoft Dynamics 365 above two labeled blocks 'SDKs' and 'NO-CODE' with arrows pointing to 'mindee' logo at the bottom.

Real-time synchronization with ERP/CRM master data and automated third-party API validation (VAT, Compliance)

Data in a vacuum has limited utility. The "Enrich" phase bridges the gap between a document and your entire enterprise ecosystem (ERP, CRM, PLM) thanks to integrations.

Flowchart showing payment validation steps: if certainty is certain or high, validate payment; if medium, trigger human review.

Automated business rule validation and high-efficiency Human-in-the-Loop workflows for edge-case validation.

Go beyond simple extraction. Build resilient document pipelines that automatically verify data against your custom business rules. Our API manages the friction between automated confidence scores and human edge-case validation, ensuring your production data is always clean, compliant, and actionable.

Puzzle pieces displaying programming language logos including Ruby, Node.js, Python, Java, and PHP, with text below reading 'Also available on' followed by logos for Zapier, Make, and n8n.

Integrate Mindee into your workflow in minutes with SDKs & no-code tools

Go live in minutes using our verified Zapier & Make.comapp with zero coding, or integrate seamlessly via our well-documented REST API built for developers. SDKs available for Python, Node.JS, Java, Ruby, PHP.

Integrations details

security soc2 and gdpr

Enterprise-grade security

Our API has a SOC 2 Type II certified infrastructure and is GDPR Compliant to ensure your file information remains protected at all times.

EU or US hosting available

GDPR, CCPA Compliant

Learn more

Developers and technical profiles already used it !

Add modern AI-based Mindee OCR API to your product, in minutes.

Mindee is an integrated document processing platform backed by reliable AI technology. The service has an intuitive and user-friendly interface and provides highly accurate results extracting data from various document types, especially financial receipts and invoices, which are relatively complex and require specialized optical character recognition (OCR) services. The platform provides seamless integration with our current data processing workflows through customizable APIs, allowing for efficient data extraction and automation.

quote

on G2

Mindee is a software that helps us to convert all of our physical business data like bills, invoices, warranty cards, calendar, recipts received to us into a digital documents that can be stored in our drive and can be uploaded in different type of Excel sheets so that all the updates can be maintained and a proper analytics of transactions can be kept by the financial team

quote

on G2

Mindee is a web based tool that help us in scanning and reading different type of documents like identity cards, invoices, proposal plans etc and extract all the information with its AI and then it provides all the information and data associated with these documents a structured way.

quote

on G2

Excellent. In addition to their great product, the sales team has always been proactive on how they could help us leverage the maximum results from their product. It was like having an additional product manager on our side

quote

on Capterra

Mindee works reliably and delivers good performance. The OCR data is accurate, and the API is stable. It works like a charm.

quote

on Capterra

Mindee is a web based tool that help us in scanning and reading different type of documents like identity cards, invoices, proposal plans etc and extract all the information with its AI and then it provides all the information and data associated with these documents a structured way.

quote

on Capterra

+15M documents processed monthly
Start to auto-crop files, extract data

Already +500 active users

14-day free trial

No credit card

Screenshot of a software interface showing extracted fields from an invoice including supplier phone number, customer company registration, JSON data, and highlighted text boxes for employee ID and pay date.

FAQ to know more about Mindee's API

What is automated multiple cropped documents ?

Automated multiple cropped documents is a specialized computer vision feature that detects, isolates, and crops individual records scanned together on a single page.

Instead of treating a scan of several receipts or IDs as one image, the API identifies the physical boundaries of each item. It then creates separate, high-resolution standalone files for each record, ensuring that the downstream extraction engine processes them individually for maximum accuracy.

What are examples of automated multiple cropped documents?

The most common use case is in expense management, where an employee might scan three or four small taxi receipts and a restaurant bill on a single A4 or letter-sized page.

Another core example is identity verification (KYC), such as scanning the front and back of a driver's license or multiple ID cards on the same flatbed scanner.

In the medical field, this technology is used to digitize several laboratory labels or prescription stickers scanned onto a single sheet.

By isolating these items, the system ensures that a "lunch receipt" doesn't get merged with a "taxi fare" in your accounting database. You can check more real-life examples of how companies leverage this technology by visiting customer stories.

How does automated multiple cropped documents work ?

The process is a sophisticated blend of geometric analysis and edge detection. When a single page is uploaded, Mindee’s vision pipeline performs a "spatial scan" to find high-contrast borders that indicate a physical object's edge.

  • Object detection: The AI identifies how many distinct items are on the page.
  • Bounding box generation: It draws a precise "box" around each item, even if they are placed at an angle (this is where "auto-deskewing" happens).
  • Cropping & de-noising: The system crops each box into a new, individual image file and clean the quality.
  • Individual processing: Each new file is sent to the relevant extraction model (e.g., the Receipt API) as if it had been uploaded on its own, eliminating cross-talk between different documents.

How to auto-crop multiple images or PDFs at once?

Manually cropping images/PDFs in a tool like Photoshop or using basic Python scripts is slow and doesn't scale.

To auto-crop multiple images/PDFs at once for a production-grade workflow, you should integrate an OCR API that includes a dedicated pre-processing layer. Mindee’s API handles this automatically: when you send a single scan containing multiple items, the vision engine detects the boundaries and performs the crop in milliseconds.

For developers, this means you can accept "bulk scans" from users without writing complex image‑processing logic, significantly accelerating your development cycle and improving the end-user experience.