Adaptive scene‐text binarisation on images captured by smartphones. Issue 7 (1st July 2016)

• Record Type: Journal Article
• Authors: Belhedi, Amira; Marcotegui, Beatriz
• Is Part Of: IET image processing. Volume 10:Issue 7(2016)
• Page Start: 515
• Page End: 523
• Publication Date: 2016-07-01
• Subjects: smart phones -- feature extraction -- image capture -- text detection; adaptive scene‐text binarisation method -- smartphones -- visually‐impaired people assistance -- local thresholding process -- image content -- problematic parameter setting -- heterogeneous database -- adaptive window extraction -- morphological operator -- thresholding windows -- local Otsu algorithm -- Niblack method -- Sauvola method -- Wolf method -- TMMS method -- maximally‐stable extremal region method -- annotated characters -- classical binarisation method -- degraded images -- low‐contrasted images -- blurred images; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2015.0695
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : The authors address, in this study, a new adaptive binarisation method on images captured by smartphones. This work is part of an application for visually impaired people assistance, which aims at making text information accessible to people who cannot read it. The main advantage of the proposed method is that the windows underlying the local thresholding process are automatically adapted to the image content. This avoids the problematic parameter setting of local thresholding approaches, difficult to adapt to a heterogeneous database. The adaptive windows are extracted based on ultimate opening (a morphological operator) and then used as thresholding windows to perform a local Otsu's algorithm. The authors' method is evaluated and compared with the Niblack, Sauvola, Wolf, toggle mapping morphological segmentation (TMMS) and maximally stable extremal regions methods on a new challenging database introduced by them. Their database is acquired by visually impaired people in real conditions. It contains 4000 annotated characters (available online for research purposes). Experiments show that the proposed method outperforms classical binarisation methods for degraded images such as low‐contrasted or blurred images, very common in their application.