Seite - 42 - in Document Image Processing
Bild der Seite - 42 -
Text der Seite - 42 -
J. Imaging 2018,4, 80
Figure 14. Application of the word-spotting system [25], before (above) and after (below)
slantcorrection.
4.Conclusions
In this paper, a technique was presented for slant estimation and removal for the entire
document page, without requiring line or word segmentation. The proposed technique is
recommendedforhistoricaldocument images that includehomogenousslant throughout thepage.
Thissegmentation-free techniqueguarantees theminimizationofextranoise thatcouldbe introduced
since thesegmentationprocedure, inhistoricaldocument images,where the text isverydense,would
leavebehindsmall strokesandotherkindofnoise (points, lines).
Experimental resultswere provided for four databases: PrintDB,which contains artificially
slantedprintedtext toprovetheaccuracyof the technique;TrigraphSlant,aknownDBofslant text;
42
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