Marginal noise removal of document images

Fan, Kuo-Chin; Wang, Yuan-Kai; Lay, Tsann Ran

doi:10.1016/s0031-3203(01)00205-9

Cited by 62 publications

(32 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pan et al [29] correct uneven illumination and remove wood grain and shading on images of text incised on wood tablets by filtering: this allows handwritten strokes to be more easily extracted. Removing shades in document margins produced while scanning thick documents with a region growing method has been studied by Fan et al [17]. Shades in the background can also be detected by morphological operations and lightened for removal [28].…”

Section: Enhancement Of Historical Printed Document Images By Combinimentioning

confidence: 99%

Enhancement of historical printed document images by combining Total Variation regularization and Non-local Means filtering

Likforman-Sulem

Darbon

Smith

2011

Image and Vision Computing

View full text Add to dashboard Cite

This is an author-produced, peer-reviewed version of this article. produce an image with a cleaner background while keeping character details. The second step is applied to the cleaner image and consists of a filter based on non-local means: character edges are smoothed by searching for similar patch images in pixel neighborhoods. The document images to be enhanced are real historical printed documents from several periods which include several defects in their background and on character edges. These defects result from scanning, paper aging and bleedthrough. The proposed method enhances document images by combining the total variation and the non-local means techniques in order to improve OCR recognition.The method is shown to be more powerful than when these techniques are used alone and than other enhancement methods.

show abstract

Section: Enhancement Of Historical Printed Document Images By Combinimentioning

confidence: 99%

Enhancement of historical printed document images by combining Total Variation regularization and Non-local Means filtering

Likforman-Sulem

Darbon

Smith

2011

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…1 The partial support of this research by DARPA through BBN/DARPA Award HR001108C0004 and the US Government through NSF Award 1150713501 is gratefully acknowledged Ink blobs, salt-n-pepper [3], stray marks, marginal noise [4] are, in general, independent of location, size or other properties of text data in the document image. Recorded images having this type of noise, can be expressed as the sum of true image I(i, j) and the noise N (i, j) as R(i, j) = I(i, j) + N (i, j) Blur, pixel-shift or bleed-through [12] on other hand, manifest themselves differently depending on the content.…”

Section: Introductionmentioning

confidence: 99%

“…Unwanted punched holes and stray marks exhibit regularity in their shapes while ruled lines [13,14] show periodicity in their positions as well. On the other hand, noise such has ink blobs, complex background binarized patterns, marginal noise [4] and salt-n-pepper [3,1] often lack any consistent property. This 'irregular noise' has typically been classified with simple rule based features.…”

Section: Introductionmentioning

confidence: 99%

“…al. [4] assumes length, position and neighborhood of noise to detect and remove the noise. Liang et al [5] depend on periodicity and regularity of noise to get rid of it.…”

Section: Introductionmentioning

confidence: 99%

“…far as we know, there has been no collective work on the detection and removal of clutter, without removing or further degrading the attached text, in binary document images. Fan, Wang and Kay [4] detect and remove marginal noise regions based on three assumptions of shape, length and position. The technique does fairly well at removing only the marginal noise without the attached text.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Clutter noise removal in binary document images

Agrawal

Doermann

2013

IJDAR

View full text Add to dashboard Cite

The paper presents a clutter detection and removal algorithm for complex document images. The distance transform based approach is independent of clutter's position, size, shape and connectivity with text. Features are based on a residual image obtained by analysis of the distance transform and clutter elements, if present, are identified with an SVM classifier. Removal is restrictive, so text attached to the clutter is not deleted in the process. The method was tested on a collection of degraded and noisy, machine-printed and handwritten Arabic and English text documents. Results show pixel-level accuracies of 97.5% and 95% for clutter detection and removal respectively.This approach was also extended with a noise detection and removal model for documents having a mix of clutter and salt-n-pepper noise.

show abstract

Background Removal of Document Images Acquired Using Portable Digital Cameras

Silva

Lins

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Marginal noise removal of document images

Cited by 62 publications

References 18 publications

Enhancement of historical printed document images by combining Total Variation regularization and Non-local Means filtering

Enhancement of historical printed document images by combining Total Variation regularization and Non-local Means filtering

Clutter noise removal in binary document images

Background Removal of Document Images Acquired Using Portable Digital Cameras

Contact Info

Product

Resources

About