Tool for automatic tuning of binarisation techniques. Issue 12 (1st December 2018)

• Record Type: Journal Article
• Authors: Kefali, Abderrahmane; Sari, Toufik
• Is Part Of: IET image processing. Volume 12:Issue 12(2018)
• Page Start: 2192
• Page End: 2203
• Publication Date: 2018-12-01
• Subjects: image segmentation -- neural nets -- document image processing -- learning (artificial intelligence); automatic parameterisation -- adaptive parameterisation -- binarisation techniques -- optimal parameter values -- training set -- automatic tuning -- optimum parameter values -- image collection -- artificial neural network -- trained ANN; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.5132
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Most of the proposed binarisation methods include parameters that must be set correctly before use. The determination of the values of these parameters is made most of the time manually after several tests. However, the optimum parameter values differ from an image to another and therefore the parameterisation shall be carried out for each image separately. In fact, as this task is very difficult, even impossible for large collections of images, the tuning is usually done once for the entire image collection. In this study, the authors propose a tool for automatic and adaptive parameterisation of binarisation techniques for each image separately. The adopted methodology is based on the use of an artificial neural network (ANN) to learn the optimal parameter values of a binarisation method for a set of images (training set), based on their features, and to use the trained ANN to determine the optimal parameter values for other images not learned. Several experiments have been conducted on images of degraded documents and the obtained results are encouraging.