qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-06-09 04:09:54 +02:00
Code Issues Projects Releases Wiki Activity

Update README.md

Browse source
This commit is contained in:
Clemens Neudecker 2022-09-14 15:26:36 +02:00 • committed by GitHub
parent ffc7f82906
commit 5ca857018b
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 15 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

30
README.md
View file

@ -38,21 +38,21 @@ eynollah -i <image file name> -o <directory to write output> -m <directory of mo
The following options can be used to further configure the processing: The following options can be used to further configure the processing:
```sh ```
-fl: perform full layout analysis including detection of marginalia and drop capitals -fl perform full layout analysis including detection of marginalia and drop capitals
-ae: allow resizing and enhancing the input image, a rescaled and enhanced image is saved to the output directory -tab try to detect tables
-as: allow scaling - check whether the input image needs rescaling or not -light apply a faster but simpler method for main region detection and deskewing
-cl: extract contours of curved textlines instead of rectangle bounding boxes -ae allow resizing and enhancing the input image, the enhanced image is saved to the output directory
-si <directory>: save image regions detected in documents to this directory -as allow scaling - automatically check whether the input image needs scaling or not
-sd <directory>: save deskewed image to this directory -ib allow binarization of the input image
-sa <directory>: save plot of layout detection to this directory -ho ignore headers for reading order prediction
-tab: try to detect tables -cl extract contours of curved textlines instead of rectangle bounding boxes
-ib: allow binarization of the input image -ep enables plotting. This MUST always be used with `-sl`, `-sd`, `-sa`, `-si` or `-ae` options
-ho: ignore headers in reading order detection -di <directory> process all images in a directory in batch mode
-sl <directory>: save plots of layout detection to this directory -si <directory> save image regions detected in documents to this directory
-ep: save a plot. This should be used alongside with `-sl`, `-sd`, `-sa`, `-si` or `-ae` options -sd <directory> save deskewed image to this directory
-light: apply a faster but simpler method for main region detection and deskewing -sl <directory> save layout prediction as plot to this directory
-di <directory>: process all images in a directory in batch mode -sa <directory> save all outputs (plot, enhanced or binary image and layout prediction) to this directory
``` ```
The tool performs better with RGB images as input than with greyscale or binarized images. The tool performs better with RGB images as input than with greyscale or binarized images.