کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6939719 | 1449973 | 2018 | 40 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Binarization of degraded document images based on hierarchical deep supervised network
ترجمه فارسی عنوان
برداشتن تصاویر سند تخریب شده بر اساس شبکه سلسله مراتبی تحت نظارت
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
تصویربرداری سند تصویری، شبکه عصبی متقاطع، تجزیه و تحلیل سند،
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
چشم انداز کامپیوتر و تشخیص الگو
چکیده انگلیسی
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.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Pattern Recognition - Volume 74, February 2018, Pages 568-586
Journal: Pattern Recognition - Volume 74, February 2018, Pages 568-586
نویسندگان
Quang Nhat Vo, Soo Hyung Kim, Hyung Jeong Yang, Gueesang Lee,