[Source](https://sheaf.us/scoreboard-ocr-accuracy.html)

Scoreboard

# OCR accuracy: the values each engine reads

Which checked values each OCR engine reads correctly, from the PDF and from the page image, with time and cost.

Its key points, its tables, how it was scored and its log load from [/api/public/scoreboards/ocr-accuracy](/api/public/scoreboards/ocr-accuracy).

## Test documents

[Test set A](test-set-cfpb-disclosures-digital-and-image.md) and [Test set B](test-set-cfpb-tables-side-by-side-digital-and-image.md): each page with a numbered bounding box on every checked value, and the answers.

## Glossary

| Term | Definition |
| --- | --- |
| OCR | Optical character recognition: reading the text, tables and marks of a page from its image or PDF. |
| engine | An OCR product or model that reads a page and returns its text, such as Mistral OCR, Landing AI or Reducto. |
| block | One part of a page as an engine returns it: a paragraph, a table, a heading or a figure. |
| bounding box | The rectangle that marks where something is printed on the page. |
| table cell | One value of a table, where a row and a column meet. |
| form field | A label on a form and the value written for it. |
| grounding | Linking each value of a reading to its bounding box on the page. |
| ground truth | The correct answers for a page, one fact per value, checkbox, choice or signature. Every reading is scored against them. |
| test set | The pages a scoreboard is measured on, with their ground truth. |
| grader | The program or model that compares a reading with the ground truth and counts what is right. |