2019-12-09 12:44:05 +01:00
|
|
|
dinglehopper
|
|
|
|
|
============
|
2019-08-14 15:32:50 +02:00
|
|
|
|
2020-06-08 18:27:20 +02:00
|
|
|
dinglehopper is an OCR evaluation tool and reads
|
|
|
|
|
[ALTO](https://github.com/altoxml),
|
|
|
|
|
[PAGE](https://github.com/PRImA-Research-Lab/PAGE-XML) and text files. It
|
|
|
|
|
compares a ground truth (GT) document page with a OCR result page to compute
|
|
|
|
|
metrics and a word/character differences report.
|
2019-08-14 18:29:49 +02:00
|
|
|
|
2021-02-10 18:22:52 +01:00
|
|
|
[](https://circleci.com/gh/qurator-spk/dinglehopper)
|
2019-08-14 18:29:49 +02:00
|
|
|
|
2019-12-09 12:44:05 +01:00
|
|
|
Goals
|
|
|
|
|
-----
|
|
|
|
|
* Useful
|
|
|
|
|
* As a UI tool
|
|
|
|
|
* For an automated evaluation
|
|
|
|
|
* As a library
|
|
|
|
|
* Unicode support
|
2019-08-15 10:35:26 +02:00
|
|
|
|
2019-12-09 12:44:05 +01:00
|
|
|
Installation
|
|
|
|
|
------------
|
|
|
|
|
It's best to use pip, e.g.:
|
|
|
|
|
~~~
|
|
|
|
|
sudo pip install .
|
|
|
|
|
~~~
|
2019-08-15 17:52:41 +02:00
|
|
|
|
2019-12-09 12:44:05 +01:00
|
|
|
Usage
|
|
|
|
|
-----
|
|
|
|
|
~~~
|
2020-06-08 18:26:21 +02:00
|
|
|
Usage: dinglehopper [OPTIONS] GT OCR [REPORT_PREFIX]
|
|
|
|
|
|
|
|
|
|
Compare the PAGE/ALTO/text document GT against the document OCR.
|
|
|
|
|
|
2020-09-30 17:58:05 +02:00
|
|
|
dinglehopper detects if GT/OCR are ALTO or PAGE XML documents to extract
|
|
|
|
|
their text and falls back to plain text if no ALTO or PAGE is detected.
|
|
|
|
|
|
2020-06-08 18:26:21 +02:00
|
|
|
The files GT and OCR are usually a ground truth document and the result of
|
|
|
|
|
an OCR software, but you may use dinglehopper to compare two OCR results.
|
|
|
|
|
In that case, use --no-metrics to disable the then meaningless metrics and
|
|
|
|
|
also change the color scheme from green/red to blue.
|
|
|
|
|
|
2020-09-24 20:56:50 +02:00
|
|
|
The comparison report will be written to $REPORT_PREFIX.{html,json}, where
|
2020-09-30 17:58:05 +02:00
|
|
|
$REPORT_PREFIX defaults to "report". The reports include the character
|
|
|
|
|
error rate (CER) and the word error rate (WER).
|
2020-09-24 20:56:50 +02:00
|
|
|
|
2020-10-20 19:33:39 +02:00
|
|
|
By default, the text of PAGE files is extracted on 'region' level. You may
|
|
|
|
|
use "--textequiv-level line" to extract from the level of TextLine tags.
|
|
|
|
|
|
2020-06-08 18:26:21 +02:00
|
|
|
Options:
|
|
|
|
|
--metrics / --no-metrics Enable/disable metrics and green/red
|
2020-10-20 19:33:39 +02:00
|
|
|
--textequiv-level LEVEL PAGE TextEquiv level to extract text from
|
2020-10-15 16:09:17 +02:00
|
|
|
--progress Show progress bar
|
2020-06-08 18:26:21 +02:00
|
|
|
--help Show this message and exit.
|
|
|
|
|
~~~
|
|
|
|
|
|
|
|
|
|
For example:
|
|
|
|
|
~~~
|
2019-12-09 12:44:05 +01:00
|
|
|
dinglehopper some-document.gt.page.xml some-document.ocr.alto.xml
|
|
|
|
|
~~~
|
|
|
|
|
This generates `report.html` and `report.json`.
|
2019-08-15 17:52:41 +02:00
|
|
|
|
2020-10-21 19:31:53 +02:00
|
|
|
|
2019-08-15 17:25:54 +02:00
|
|
|
|
2020-10-21 16:51:53 +02:00
|
|
|
### dinglehopper-extract
|
|
|
|
|
The tool `dinglehopper-extract` extracts the text of the given input file on
|
|
|
|
|
stdout, for example:
|
|
|
|
|
|
|
|
|
|
~~~
|
|
|
|
|
dinglehopper-extract --textequiv-level line OCR-D-GT-PAGE/00000024.page.xml
|
|
|
|
|
~~~
|
|
|
|
|
|
|
|
|
|
### OCR-D
|
2019-12-09 12:44:05 +01:00
|
|
|
As a OCR-D processor:
|
2019-11-18 16:32:42 +01:00
|
|
|
~~~
|
2020-06-09 18:30:36 +02:00
|
|
|
ocrd-dinglehopper -I OCR-D-GT-PAGE,OCR-D-OCR-TESS -O OCR-D-OCR-TESS-EVAL
|
2019-11-18 16:32:42 +01:00
|
|
|
~~~
|
2019-12-09 12:44:05 +01:00
|
|
|
This generates HTML and JSON reports in the `OCR-D-OCR-TESS-EVAL` filegroup.
|
2019-12-09 11:57:16 +01:00
|
|
|
|
2020-10-21 16:51:53 +02:00
|
|
|
The OCR-D processor has these parameters:
|
2020-06-09 18:29:59 +02:00
|
|
|
|
2020-10-21 16:51:53 +02:00
|
|
|
| Parameter | Meaning |
|
|
|
|
|
| ------------------------- | ------------------------------------------------------------------- |
|
|
|
|
|
| `-P metrics false` | Disable metrics and the green-red color scheme (default: enabled) |
|
|
|
|
|
| `-P textequiv_level line` | (PAGE) Extract text from TextLine level (default: TextRegion level) |
|
|
|
|
|
|
|
|
|
|
For example:
|
2020-06-09 18:29:59 +02:00
|
|
|
~~~
|
2020-10-15 15:37:51 +02:00
|
|
|
ocrd-dinglehopper -I ABBYY-FULLTEXT,OCR-D-OCR-CALAMARI -O OCR-D-OCR-COMPARE-ABBYY-CALAMARI -P metrics false
|
2020-06-09 18:29:59 +02:00
|
|
|
~~~
|
|
|
|
|
|
2020-10-08 16:59:50 +02:00
|
|
|
Developer information
|
|
|
|
|
---------------------
|
2020-10-08 17:14:29 +02:00
|
|
|
*Please refer to [README-DEV.md](README-DEV.md).*
|
