Ensemble of steerable local neighbourhood grey-level information for binarization

F. Kasmin, Azizi Abdullah, A. S. Prabuwono

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Steerable filters are very useful in vision and image processing because the response of the filters at various orientations can be examined and manipulated, which is useful for texture analysis and image denoising. In supervised binarization, a set of grey-level values can be used to represent a particular pixel and to determine whether it belongs to the foreground or background. However, extensive noise may be produced in the resultant images if the chosen grey-level values are insufficient to describe the pixel. This may occur when some of the pixels are wrongly classified. To overcome this problem, the advantages of steerable filters are employed in proposed steerable local neighbourhood (SLN) of grey-level information methods to characterise pixels in images. The proposed methods use a support vector machine to classify each pixel using SLN grey-level information. Sets of normalised intensities of grey-level values are generated according to the orientations at 0°, 45°, 90°, 135°, 180°, 225°, 270° and 315°. These sets of feature vectors contain the vectors of the local neighbourhood of grey-level information of each pixel. Document and retinal images are used to train and test the accuracy of the proposed classifier. On the basis of the results obtained for the training images, weights are applied to every SLN. Then, the ensemble of steerable local neighbourhood methods, namely the weighted addition rule and the weighted product rule, are used to combine all the SLNs’ grey-level information. The results of the proposed methods are promising and clearly show a significant improvement in terms of accuracy compared to that of other methods.

Original languageEnglish
Pages (from-to)8-15
Number of pages8
JournalPattern Recognition Letters
Volume98
DOIs
Publication statusPublished - 15 Oct 2017

Fingerprint

Pixels
Image denoising
Support vector machines
Image processing
Classifiers
Textures

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Ensemble of steerable local neighbourhood grey-level information for binarization. / Kasmin, F.; Abdullah, Azizi; Prabuwono, A. S.

In: Pattern Recognition Letters, Vol. 98, 15.10.2017, p. 8-15.

Research output: Contribution to journalArticle

@article{e44bb8d562f848809ce89d1df99437ba,
title = "Ensemble of steerable local neighbourhood grey-level information for binarization",
abstract = "Steerable filters are very useful in vision and image processing because the response of the filters at various orientations can be examined and manipulated, which is useful for texture analysis and image denoising. In supervised binarization, a set of grey-level values can be used to represent a particular pixel and to determine whether it belongs to the foreground or background. However, extensive noise may be produced in the resultant images if the chosen grey-level values are insufficient to describe the pixel. This may occur when some of the pixels are wrongly classified. To overcome this problem, the advantages of steerable filters are employed in proposed steerable local neighbourhood (SLN) of grey-level information methods to characterise pixels in images. The proposed methods use a support vector machine to classify each pixel using SLN grey-level information. Sets of normalised intensities of grey-level values are generated according to the orientations at 0°, 45°, 90°, 135°, 180°, 225°, 270° and 315°. These sets of feature vectors contain the vectors of the local neighbourhood of grey-level information of each pixel. Document and retinal images are used to train and test the accuracy of the proposed classifier. On the basis of the results obtained for the training images, weights are applied to every SLN. Then, the ensemble of steerable local neighbourhood methods, namely the weighted addition rule and the weighted product rule, are used to combine all the SLNs’ grey-level information. The results of the proposed methods are promising and clearly show a significant improvement in terms of accuracy compared to that of other methods.",
author = "F. Kasmin and Azizi Abdullah and Prabuwono, {A. S.}",
year = "2017",
month = "10",
day = "15",
doi = "10.1016/j.patrec.2017.07.014",
language = "English",
volume = "98",
pages = "8--15",
journal = "Pattern Recognition Letters",
issn = "0167-8655",
publisher = "Elsevier",

}

TY - JOUR

T1 - Ensemble of steerable local neighbourhood grey-level information for binarization

AU - Kasmin, F.

AU - Abdullah, Azizi

AU - Prabuwono, A. S.

PY - 2017/10/15

Y1 - 2017/10/15

N2 - Steerable filters are very useful in vision and image processing because the response of the filters at various orientations can be examined and manipulated, which is useful for texture analysis and image denoising. In supervised binarization, a set of grey-level values can be used to represent a particular pixel and to determine whether it belongs to the foreground or background. However, extensive noise may be produced in the resultant images if the chosen grey-level values are insufficient to describe the pixel. This may occur when some of the pixels are wrongly classified. To overcome this problem, the advantages of steerable filters are employed in proposed steerable local neighbourhood (SLN) of grey-level information methods to characterise pixels in images. The proposed methods use a support vector machine to classify each pixel using SLN grey-level information. Sets of normalised intensities of grey-level values are generated according to the orientations at 0°, 45°, 90°, 135°, 180°, 225°, 270° and 315°. These sets of feature vectors contain the vectors of the local neighbourhood of grey-level information of each pixel. Document and retinal images are used to train and test the accuracy of the proposed classifier. On the basis of the results obtained for the training images, weights are applied to every SLN. Then, the ensemble of steerable local neighbourhood methods, namely the weighted addition rule and the weighted product rule, are used to combine all the SLNs’ grey-level information. The results of the proposed methods are promising and clearly show a significant improvement in terms of accuracy compared to that of other methods.

AB - Steerable filters are very useful in vision and image processing because the response of the filters at various orientations can be examined and manipulated, which is useful for texture analysis and image denoising. In supervised binarization, a set of grey-level values can be used to represent a particular pixel and to determine whether it belongs to the foreground or background. However, extensive noise may be produced in the resultant images if the chosen grey-level values are insufficient to describe the pixel. This may occur when some of the pixels are wrongly classified. To overcome this problem, the advantages of steerable filters are employed in proposed steerable local neighbourhood (SLN) of grey-level information methods to characterise pixels in images. The proposed methods use a support vector machine to classify each pixel using SLN grey-level information. Sets of normalised intensities of grey-level values are generated according to the orientations at 0°, 45°, 90°, 135°, 180°, 225°, 270° and 315°. These sets of feature vectors contain the vectors of the local neighbourhood of grey-level information of each pixel. Document and retinal images are used to train and test the accuracy of the proposed classifier. On the basis of the results obtained for the training images, weights are applied to every SLN. Then, the ensemble of steerable local neighbourhood methods, namely the weighted addition rule and the weighted product rule, are used to combine all the SLNs’ grey-level information. The results of the proposed methods are promising and clearly show a significant improvement in terms of accuracy compared to that of other methods.

UR - http://www.scopus.com/inward/record.url?scp=85026900847&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026900847&partnerID=8YFLogxK

U2 - 10.1016/j.patrec.2017.07.014

DO - 10.1016/j.patrec.2017.07.014

M3 - Article

AN - SCOPUS:85026900847

VL - 98

SP - 8

EP - 15

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

SN - 0167-8655

ER -