SBB
/

Image-to-Image
TF-Keras
pixelwise-segmentation
cneud commited on
Commit
5376dbb
·
1 Parent(s): a51920c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -5,9 +5,9 @@ license: apache-2.0
5
  ---
6
  # About `sbb_binarization`
7
 
8
- This is a model for document image binarization. It can be used
9
- to convert all pixels in a color or grayscale document image to
10
- only black or white pixels. The main purpose is to improve the
11
  contrast between foreground (text) and background (paper) for
12
  purposes of OCR. The model is based on a `ResNet50-Unet` model.
13
 
 
5
  ---
6
  # About `sbb_binarization`
7
 
8
+ This is a CNN model for document image binarization. It can be
9
+ used to convert all pixels in a color or grayscale document image
10
+ to only black or white pixels. The main purpose is to improve the
11
  contrast between foreground (text) and background (paper) for
12
  purposes of OCR. The model is based on a `ResNet50-Unet` model.
13