BedSr-Net: A deep shadow removal network from a single document image
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages
12902-12911
Date Issued
2020
Author(s)
Abstract
Removing shadows in document images enhances both the visual quality and readability of digital copies of documents. Most existing shadow removal algorithms for document images use hand-crafted heuristics and are often not robust to documents with different characteristics. This paper proposes the Background Estimation Document Shadow Removal Network (BEDSR-Net), the first deep network specifically designed for document image shadow removal. For taking advantage of specific properties of document images, a background estimation module is designed for extracting the global background color of the document. During the process of estimating the background color, the module also learns information about the spatial distribution of background and non-background pixels. We encode such information into an attention map. With the estimated global background color and attention map, the shadow removal network can better recover the shadow-free image. We also show that the model trained on synthetic images remains effective for real photos, and provide a large set of synthetic shadow images of documents along with their corresponding shadow-free images and shadow masks. Extensive quantitative and qualitative experiments on several benchmarks show that the BEDSR-Net outperforms existing methods in enhancing both the visual quality and readability of document images. ©2020 IEEE.
Other Subjects
Benchmarking; Color; Pattern recognition; Background estimation; Background pixels; Document images; Qualitative experiments; Shadow removal; Specific properties; Synthetic images; Visual qualities; Image enhancement
Type
conference paper