Projection-based text line segmentation with a variable threshold
International Journal of Applied Mathematics and Computer Science, Tome 27 (2017) no. 1, p. 195.

Voir la notice de l'article dans European Digital Mathematics Library

Document image segmentation into text lines is one of the stages in unconstrained handwritten document recognition. This paper presents a new algorithm for text line separation in handwriting. The developed algorithm is based on a method using the projection profile. It employs thresholding, but the threshold value is variable. This permits determination of low or overlapping peaks of the graph. The proposed technique is shown to improve the recognition rate relative to traditional methods. The algorithm is robust in text line detection with respect to different text line lengths.
Mots-clés : document image processing, handwritten text line segmentation, projection profile, off-line cursive script recognition 
@article{IJAMCS_2017__27_1_288098,
     author = {Roman Ptak and Bartosz Zygad{\l}o and Olgierd Unold},
     title = {Projection-based text line segmentation with a variable threshold},
     journal = {International Journal of Applied Mathematics and Computer Science},
     pages = {195},
     publisher = {mathdoc},
     volume = {27},
     number = {1},
     year = {2017},
     language = {en},
     url = {https://geodesic-test.mathdoc.fr/item/IJAMCS_2017__27_1_288098/}
}
TY  - JOUR
AU  - Roman Ptak
AU  - Bartosz Zygadło
AU  - Olgierd Unold
TI  - Projection-based text line segmentation with a variable threshold
JO  - International Journal of Applied Mathematics and Computer Science
PY  - 2017
SP  - 195
VL  - 27
IS  - 1
PB  - mathdoc
UR  - https://geodesic-test.mathdoc.fr/item/IJAMCS_2017__27_1_288098/
LA  - en
ID  - IJAMCS_2017__27_1_288098
ER  - 
%0 Journal Article
%A Roman Ptak
%A Bartosz Zygadło
%A Olgierd Unold
%T Projection-based text line segmentation with a variable threshold
%J International Journal of Applied Mathematics and Computer Science
%D 2017
%P 195
%V 27
%N 1
%I mathdoc
%U https://geodesic-test.mathdoc.fr/item/IJAMCS_2017__27_1_288098/
%G en
%F IJAMCS_2017__27_1_288098
Roman Ptak; Bartosz Zygadło; Olgierd Unold. Projection-based text line segmentation with a variable threshold. International Journal of Applied Mathematics and Computer Science, Tome 27 (2017) no. 1, p. 195. https://geodesic-test.mathdoc.fr/item/IJAMCS_2017__27_1_288098/