Texture segmentation using adaptive Gabor filters based on HVS

Bi, Sheng; Liang, Dequn

doi:10.1117/12.650246

Cited by 3 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quantitative comparison shows that the proposed method produces similar segmentation with percentage errors of ≈ 3.1% and ≈ 3.5%, respectively compared to the results in [10], with especially better discrimination along the boundaries. Secondly, we compared our results in [4] qualitatively and the results are shown in Figure 10.…”

Section: Different Region Shapesmentioning

confidence: 96%

“…However, in homogeneous textures the method shows good segmentation results as shown in the last two rows of Figure 8. The next section compares the algorithm with two proposed methods in the literatures [10,4]. Firstly, the results are compared with an algorithm proposed by [10] based on the two images shown in Figure 9.…”

Section: Different Region Shapesmentioning

confidence: 98%

“…This process can be done using several techniques such as Discrete Wavelet Transformation (DWT) [14], Gabor Filters [19,15,4,38], GLCM [17,32,7], and Local Binary Patterns (LBP) [24]. Numerous investigations have been carried out regarding the set of features to be considered for use in the algorithm.…”

Section: Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Texture segmentation using different orientations of GLCM features

Rampun

Strange

Zwiggelaar

2013

Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Application

View full text Add to dashboard Cite

This paper describes the development of a new texture based segmentation algorithm which uses a set of features extracted from Grey-Level Co-occurrence Matrices. The proposed method segments different textures based on noise reduced features which are effective texture descriptor. Each of the features is processed including normalisation and noise removal. Principal Component Analysis is used to reduce the dimensionality of the resulting feature space. Gaussian Mixture Modelling is used for the subsequent segmentation and false positive regions are removed using morphology. The evaluation includes a wide range of textures (more than 80 Brodatz textures) and in comparison (both qualitative and quantitative) with state of the art techniques very good segmentation results have been obtained.

show abstract

Section: Different Region Shapesmentioning

confidence: 96%

Section: Different Region Shapesmentioning

confidence: 98%

See 1 more Smart Citation

Texture segmentation using different orientations of GLCM features

Rampun

Strange

Zwiggelaar

2013

Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Application

View full text Add to dashboard Cite

show abstract

“…We take each filter ) ( , z v µ ψ as a Gabor channel, the 64 filters form a set of parallel and quasi-independent channels which are sensitive to visual signal with some specific scale v and orientation µ [18][19][20], thus the 2D Gaborface representations from different channels seems to provide an observer with multiple cues and this in itself facilitates data fusion [14]. Consequently we shall study three approaches to divide the 64 Gaborface representations from different channels into groups, and simultaneously apply classification algorithm on these feature groups, and then perform the decision level fusion to obtain the final classification results.…”

Section: B Multichannel Gaborface Representation Modelmentioning

confidence: 99%

Face Recognition using Gaborface-based 2DPCA and (2D)2PCA Classification with Ensemble and Multichannel Model

Wang¹,

Li²,

Wang³

et al. 2007

2007 IEEE Symposium on Computational Intelligence in Security and Defense Applications

View full text Add to dashboard Cite

This paper introduces Gaborface-based 2DPCA and (2D) 2 PCA classification method based on 2D Gaborface matrices rather than transformed 1D feature vectors. Two kinds of strategies to use the bank of Gaborfaces are proposed: ensemble Gaborface representation (EGFR) and multichannel Gaborface representation (MGFR). The feasibility of our method is proved with the experimental results on the ORL and Yale databases. In particular, the MGFR-based (2D) 2 PCA method achieves 100% recognition accuracy for ORL database, and 98.89% accuracy for Yale database with five training samples per class.

show abstract

“…We take each filter w l,v (z) as a Gabor channel, the 64 filters form a set of parallel and quasi-independent channels which are sensitive to visual signal with some specific scale v and orientation l [16,21,22], thus the 2D Gaborface representations from different channels seems to provide an observer with multiple cues and this in itself facilitates data fusion [15]. Consequently we shall study three approaches to divide the 64 Gaborface representations from different channels into groups, and simultaneously apply classification algorithm on these feature groups, and then perform the decision level fusion to obtain the final classification results.…”

Section: Multichannel Gaborface Representation Modelmentioning

confidence: 99%

2D Gaborface representation method for face recognition with ensemble and multichannel model

Wang

et al. 2008

Image and Vision Computing

View full text Add to dashboard Cite

Texture segmentation using adaptive Gabor filters based on HVS

Cited by 3 publications

References 8 publications

Texture segmentation using different orientations of GLCM features

Texture segmentation using different orientations of GLCM features

Face Recognition using Gaborface-based 2DPCA and (2D)2PCA Classification with Ensemble and Multichannel Model

2D Gaborface representation method for face recognition with ensemble and multichannel model

Contact Info

Product

Resources

About