Seite - 32 - in Document Image Processing
Bild der Seite - 32 -
Text der Seite - 32 -
J. Imaging 2018,4, 80
2.MaterialsandMethods
2.1. SlantDetectionAlgorithm
Asalreadymentioned, in theproposedtechnique, theslantdetectionalgorithmthat ispresented
indetail in [9] isused. Thereason is thatanalgorithmfor thedetection isneededandthisonehas
provedtobepopularandsuccessful [3].
Thisspecificalgorithmmakesuseof thedifferencebetweentheascendersanddescenders. Incase
the text isvertical, thedifference is larger (Figure3). Todetect that, ituses theWignerVilledistribution
(WVD)[21], aspace-frequencydistributionofCohen’sclass,which isgivenbythe formula
W(s, f)= +∞∫
−∞ z(s+τ/2)z∗(s−τ/2)e−2iπ fτdτ, (1)
where s the signal, f the frequency, z(s) represents theanalytical signalassociatedwith thediscrete
signalh(s), that in thepaper [9] is theverticalprojectionprofileof theword.
Figure3.Fromleft toright: slantedwords, correspondinghistogramsandmaximumintensitycurves
ofWVD(Wigner–Villedistribution).
32
zurück zum
Buch Document Image Processing"
Document Image Processing
- Titel
- Document Image Processing
- Autoren
- Ergina Kavallieratou
- Laurence Likforman-Sulem
- Herausgeber
- MDPI
- Ort
- Basel
- Datum
- 2018
- Sprache
- deutsch
- Lizenz
- CC BY-NC-ND 4.0
- ISBN
- 978-3-03897-106-1
- Abmessungen
- 17.0 x 24.4 cm
- Seiten
- 216
- Schlagwörter
- document image processing, preprocessing, binarizationl, text-line segmentation, handwriting recognition, indic/arabic/asian script, OCR, Video OCR, word spotting, retrieval, document datasets, performance evaluation, document annotation tools
- Kategorie
- Informatik