|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|152685||2018||40 صفحه PDF||سفارش دهید||11719 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Pattern Recognition, Volume 74, February 2018, Pages 568-586
The binarization of degraded document images is a challenging problem in terms of document analysis. Binarization is a classification process in which intra-image pixels are assigned to either of the two following classes: foreground text and background. Most of the algorithms are constructed on low-level features in an unsupervised manner, and the consequent disenabling of full utilization of input-domain knowledge considerably limits distinguishing of background noises from the foreground. In this paper, a novel supervised-binarization method is proposed, in which a hierarchical deep supervised network (DSN) architecture is learned for the prediction of the text pixels at different feature levels. With higher-level features, the network can differentiate text pixels from background noises, whereby severe degradations that occur in document images can be managed. Alternatively, foreground maps that are predicted at lower-level features present a higher visual quality at the boundary area. Compared with those of traditional algorithms, binary images generated by our architecture have cleaner background and better-preserved strokes. The proposed approach achieves state-of-the-art results over widely used DIBCO datasets, revealing the robustness of the presented method.