Show simple item record

AuthorAkbari Y.
AuthorAl-Maadeed, Somaya
AuthorAdam K.
Available date2022-05-19T10:23:11Z
Publication Date2020
Publication NameIEEE Access
ResourceScopus
Identifierhttp://dx.doi.org/10.1109/ACCESS.2020.3017783
URIhttp://hdl.handle.net/10576/31127
AbstractConvolutional neural networks (CNNs) have previously been broadly utilized to binarize document images. These methods have problems when faced with degraded historical documents. This paper proposes the utilization of CNNs to identify foreground pixels using novel input-generated multichannel images. To create the images, the original source image is decomposed into wavelet subbands. Then, the original image is approximated by each subband separately, and finally, the multichannel image is constituted by arranging the original source image (grayscale image) as the first channel and the approximated image by each subband as the remaining channels. To achieve the best results, two scenarios are considered, that is, two-channel and four-channel images, and then fed into two types of CNN architectures, namely, single and multiple streams. To investigate the effect of the multichannel images proposed as network inputs, the CNNs used in the architectures are three popular networks, namely, U-net, SegNet, and DeepLabv3+. The experimental results of the scenarios demonstrate that our method is more successful than the three CNNs when trained by the original source images and proves competitive performance in comparison with state-of-the-art results using the DIBCO database.
SponsorThis work was supported by the Qatar National Research Fund (a member of Qatar Foundation) through the National Priority Research Program (NPRP) under Grant NPRP 7-442-1-082.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectConvolution
Network architecture
Competitive performance
Degraded document images
Gray-scale images
Historical documents
Multichannel images
Multiple streams
State of the art
Wavelet subbands
Convolutional neural networks
TitleBinarization of Degraded Document Images Using Convolutional Neural Networks and Wavelet-Based Multichannel Images
TypeArticle
Pagination153517-153534
Volume Number8


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record