Extreme value theory based text binarization in documents and natural scenes

Basura Fernando (1) , Sezer Karaoglu (1) , Alain Trémeau (1)

1 LHC - Laboratoire Hubert Curien

This paper presents a novel image binarization method that can deal with degradations such as shadows, non-uniform illumination, low-contrast, large signal-dependent noise, smear and strain. A pre-processing procedure based on morphological operations is first applied to suppress light/dark structures connected to image border. A novel binarization concept based on difference of gamma functions is presented. Next Generalized Extreme Value Distribution (GEVD) is used to find proper threshold for binarization with a significance level. Proposed method emphasizes on region of interest (with the help of morphological operations) and generates less noisy artifacts (due to GEVD). It is much simpler than other methods and works better on degraded documents and natural scene images

Mots clés: Generalized Extreme Value Distribution; Geodesic Transform morphological reconstruction; Connected opening; Text binarization

Domaines: Traitement des images [eess.IV]

Basura Fernando, Sezer Karaoglu, Alain Trémeau. Extreme value theory based text binarization in documents and natural scenes. 3rd International Conference on Machine Vision, Dec 2010, Hong Kong, Hong Kong SAR China. pp.144-151. ⟨hal-00590644⟩