2010
DOI: 10.1117/12.840606
|View full text |Cite
|
Sign up to set email alerts
|

Effect of pre-processing on binarization

Abstract: The effects of different image pre-processing methods for document image binarization are explored. They are compared on five different binarization methods on images with bleed through and stains as well as on images with uniform background speckle. The binarization method is significant in the binarization accuracy, but the pre-processing also plays a significant role. The Total Variation method of pre-processing shows the best performance over a variety of pre-processing methods.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
5
0
4

Year Published

2010
2010
2024
2024

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 18 publications
(9 citation statements)
references
References 11 publications
0
5
0
4
Order By: Relevance
“…The binarization algorithms are (1) Otsu -a global thresholding algorithm [6], (2) Niblack -a common adaptive thresholding algorithm [4], (3) Sauvola -another adaptive binarization algorithm [8], (4) Gatos -An algorithm that is particularly suited to documents with uneven background from bleed through and stains [3] and (5) Background Estimation and Subtraction (BES) -an algorithm developed by the author that uses the Total Variation framework for image regularization [1].…”
Section: Experiments and Resultsmentioning
confidence: 99%
“…The binarization algorithms are (1) Otsu -a global thresholding algorithm [6], (2) Niblack -a common adaptive thresholding algorithm [4], (3) Sauvola -another adaptive binarization algorithm [8], (4) Gatos -An algorithm that is particularly suited to documents with uneven background from bleed through and stains [3] and (5) Background Estimation and Subtraction (BES) -an algorithm developed by the author that uses the Total Variation framework for image regularization [1].…”
Section: Experiments and Resultsmentioning
confidence: 99%
“…Finally, one may compare the binarized image with ground truth data at the pixel-level [12,13]. The main advantage of this approach is that one may add or 2.2.…”
Section: Discussionmentioning
confidence: 99%
“…Οι διαγωνισμοί, διαμέσου των εικόνων ground-truth και των μετρικών που χρησιμοποιήθηκαν, αποτέλεσαν αντικείμενο μελέτης τόσο από εμάς όσο και από άλλες ερευνητικές ομάδες [109]- [110], [157]. Τα δυαδικά αποτελέσματα των συμμετεχόντων αξιοποιήθηκαν μέσω της σχολαστικής οπτικής εξέτασης αυτών και της προσπάθειας συσχέτισή τους με τις μετρικές αξιολόγησης.…”
Section: εξελικτική πορείαunclassified
“…έγγραφα δεν αποφέρει ικανοποιητικά αποτελέσματα[39],[56],[107]-[108]. Παρόλο που η χρήση του OCR στη διαδικασία αξιολόγησης κρίνεται σημαντική, η απόδοση του OCR δεν εξαρτάται μόνο από την αποτελεσματικότητα της δυαδικής μετατροπής αλλά και από την αποτελεσματικότητα αρκετών επόμενων σταδίων[109]-[111].…”
unclassified
See 1 more Smart Citation