Paper Info
Title
A local linear level set method for the binarization of degraded historical document images
Abstract
Document image binarization is a difficult task, especially for complex document images. Nonuniform background, stains, and variation in the intensity of the printed characters are some examples of challenging document features. In this work, binarization is accomplished by taking advantage of local probabilistic models and of a flexible active contour scheme. More specifically, local linear models are used to estimate both the expected stroke and the background pixel intensities. This information is then used as the main driving force in the propagation of an active contour. In addition, a curvature-based force is used to control the viscosity of the contour and leads to more natural-looking results. The proposed implementation benefits from the level set framework, which is highly successful in other contexts, such as medical image segmentation and road network extraction from satellite images. The validity of the proposed approach is demonstrated on both recent and historical document images of various types and languages. In addition, this method was submitted to the Document Image Binarization Contest (DIBCO’09), at which it placed 3rd.
Year
DOI
Venue
2012
10.1007/s10032-011-0157-5
IJDAR
Keywords
Field
DocType
level set method · local linear modeling · multi-level classifiers · binarization,complex document image,document feature,flexible active contour scheme,historical document image,local linear level set,degraded historical document image,active contour,curvature-based force,local probabilistic model,document image binarization,background pixel intensity,local linear model
Active contour model,Computer vision,Curvature,Pattern recognition,Level set method,Computer science,Level set,Image segmentation,Pixel,Artificial intelligence,Probabilistic logic,Historical document
Journal
Volume
Issue
ISSN
15
2
1433-2825
Citations 
PageRank 
References 
16
0.68
40
Authors
3
Name
Order
Citations
PageRank
David Rivest-Hénault1635.33
Reza Farrahi Moghaddam246934.39
Mohamed Cheriet32047238.58