What is a receipt OCR?

Receipt OCR stands for Receipt Optical Character Recognition. It refers to any technology transforming an unstructured image or pdf of a receipt into structured data. This technology can be distributed as a software for developers, on the cloud (API) or as a library, allowing them to build receipt scanning features in their applications and avoid manual data entry.

Choosing the right receipt OCR for your application

Finding the right OCR technology to use for your project can be a heavy task. Whatever your use case is, criteria like extraction performances, response time, integration time, pricing, scalability… should be taken into account in order to maximize the added value in your software.
Feel free to contact us if you don’t find the answers to your questions below.

How can I test the receipt OCR API?

Our receipt API is free to test upto a specific limit and available to any user having an account on RapidAPI.
To test our APIs, you only have to create a free account and head over to the ‘Endpoints’ section. From there, you should be able to experiment via the live interface to see the data extracted from image receipt in real-time and JSON response.

Is Dodogeny’s receipt OCR API free to use?

check the pricing page https://dodogeny.com/pricing for mroe details.

Please talk to us if you want a customized plan as per your needs. we’ll be glad to help out.

How complicated is it to integrate the API?

Dodogeny’s Receipt OCR API follows HTTP standards in order to allow any developer to integrate the receipt OCR API into their applications easily.

What is the OCR accuracy?

Our receipt OCR’s accuracy is above 75%, with precision above 50% for most of the fields. These performances are computed on a data set of over 10k+ receipts.

If you want to have a feel and check out if this API works for your use case. we do provide a Basic plan to experiment ( please note that you will need to setup a RapidApi account).

Feel free to test out your receipts in the live interface (section Endpoints) to see the OCR performance on your data.

Alternatively, you can test directly receipt OCR capability through the landing page:
https://dodogeny.com/#LiveDemo

What’s the average API response time?

The processing time is around 4~7 seconds currently for a receipt image.

We are busy optimizing the OCR Engine to improve inference time. Our goal is to make sure you can create real-time user experiences in your application.

Please keep tuned to this page as we will be adding more features down the line.

Does the OCR work on low-quality images?

Yes, the OCR was trained on a lot of receipts from a wide variety of layouts and image quality and learned to process the most complex ones.

We also use data augmentation to make sure that no blur or ink stains prevent the OCR from reading the data as long as it’s readable.

And last but not least. thank you for taking the time to go through the documentation and try out our service.
As we are always optimizing the service, please give us a shout if you have any suggestions/critics/queries. 

Software Change History

---

17/03/2024

• Added Receipt Validation Feature ( First Phase)
• Started work on API Documentation (Notion)

31/01/2024

• Fixed issue in image auto-correct feature.
• Fixed skewed text issue in tilted receipt image
• Updated Integrations web page.
• Fixed emailing for website.

30/12/2023

• Added Receipt Analytics changes.
• Added minor UI changes to landing page.

23/12/2023

• Added pro-processing image capability before OCR.
• Added feature to detect image skew and auto-correct orientation.
• Fixed Live Testing section in landing page, https://dodogeny.com/#LiveDemo

02/11/2023

• Added landing page for OCR Service, https://dodogeny.com/
• Fixed issue where decimal points were ignored in item lines e.g. price and amount.
• Added contact page to web site.
• Fixed issue for nested prediction keyword for file and encoded API methods.
• Implemeted Receipt LineSegmentation business logic for accurate receipt text parsing.
• Added email capability for notification purpose.

20/11/2023

• Re-worked OCR Engine for better performance.
• Refactorized API methods to use form/multi-part instead of JSON parameters.
• Improved ConvertImageToBase64 performance for image conversions between supported image formats.
• Updated to LibVips library for image pre-processing (provides better performance than ImageMagick)
  > reference: https://www.libvips.org/
• Moved to more powerful server instance due to network outages encountered during internal testing.

04/08/2023

• Added PDF Support to following API methods to enable PDF (one-sheet) support.

ParseEncodedImageReceiptByML
ParseFileImageReceiptByML

12/05/2023

• Minor performance improvements with regards to internal OCR engine.

15/05/2023

• Added 3000 receipt images to trained dataset.

05/05/2023

• Added 1500 receipt images to trained dataset.
• Fixed language detection bug.