A Non-parametric Framework for Document Bleed-through Removal

Rowley-Brooke, Róisín; Pitié, François; Kokaram, Anil

doi:10.1109/cvpr.2013.380

Cited by 25 publications

(23 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It efficiently removes the bleed-through degradation, leaves intact the foreground text, and preserves the original look of the document. The non-parametric method of [16] (Figure 3c), although retaining foreground text and background texture, leaves clearly visible bleed-through imprints in some cases. The recent method presented in [7] (Figure 3d) produces better results, but some strokes of the foreground text are missing.…”

Section: Resultsmentioning

confidence: 99%

“…We compared the proposed method with other state-of-the-art methods including [7,16]. For evaluation, we used images from the well known database of ancient documents presented in [63,64].…”

Section: Resultsmentioning

confidence: 99%

“…A visual comparison of the proposed method with other state-of-the-art methods is presented in Figure 3. The reported results for [16] are obtained from the online available ancient manuscripts database (https://www.isos.dias.ie/). In the ground truth images, obtained from [7], foreground text and bleed through are manually labeled.…”

Section: Resultsmentioning

confidence: 99%

“…A non-blind ICA method is outlined in [14]. Other methods of this category are proposed in [15][16][17]. The performance of the non-blind methods depends on the accurate registration of recto and verso sides of the document, which is a non-trivial pre-processing step.…”

Section: Introductionmentioning

confidence: 99%

“…However, the random pixel selection produces salt and pepper like artifacts in regions with large bleed-through. In [6,16], as a preliminary step, a "clean" background for the entire image is estimated, but this is usually a very laborious task. In bleed-through removal, the desired restored image is the one where the foreground and background texture is preserved as much as possible.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Non-Local Sparse Image Inpainting for Document Bleed-Through Removal

et al. 2018

View full text Add to dashboard Cite

Bleed-through is a frequent, pervasive degradation in ancient manuscripts, which is caused by ink seeped from the opposite side of the sheet. Bleed-through, appearing as an extra interfering text, hinders document readability and makes it difficult to decipher the information contents. Digital image restoration techniques have been successfully employed to remove or significantly reduce this distortion. This paper proposes a two-step restoration method for documents affected by bleed-through, exploiting information from the recto and verso images. First, the bleed-through pixels are identified, based on a non-stationary, linear model of the two texts overlapped in the recto-verso pair. In the second step, a dictionary learning-based sparse image inpainting technique, with non-local patch grouping, is used to reconstruct the bleed-through-contaminated image information. An overcomplete sparse dictionary is learned from the bleed-through-free image patches, which is then used to estimate a befitting fill-in for the identified bleed-through pixels. The non-local patch similarity is employed in the sparse reconstruction of each patch, to enforce the local similarity. Thanks to the intrinsic image sparsity and non-local patch similarity, the natural texture of the background is well reproduced in the bleed-through areas, and even a possible overestimation of the bleed through pixels is effectively corrected, so that the original appearance of the document is preserved. We evaluate the performance of the proposed method on the images of a popular database of ancient documents, and the results validate the performance of the proposed method compared to the state of the art.

show abstract

Section: Resultsmentioning

confidence: 99%