Structure adaptive anisotropic filtering

Yang, Guang‐Zhong; Burger, Peter; Firmin, D. N.; Underwood, S. R.; Longmore, D. B.

doi:10.1049/cp:19950753

Cited by 19 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this way, the influence of the mean preserving term will be higher within homogeneous regions than near the boundaries. The favoured flux along the direction of the detected structures intuitively follows the same idea as of other approaches as proposed by Weickert, 4 Krissian 10 or Yang et al 15 However, this step depends on the likelihood of a voxel to be part of a boundary, in which case, a new orthonormal basis is computed following the normal to the surface. The scale dependency is given by the number of levels in which the original image is subsampled.…”

Section: Introductionmentioning

confidence: 92%

“…This strategy can be related to other filters performing directional local averaging, or within an anisotropic diffusion framework taking into account the direction of the structures. 4,10,15 However, in this work the detection of the structure, and consequently the flux, is based on global and local information. This is achieved by first detecting gross boundaries based on a likelihood operator as described in section 2.3, after which a local, boundary-aligned coordinate system is computed for the boundaries (Figure 4), while keeping the original coordinate system for the remaining areas.…”

Section: Flux Computation At a Single Level By F Lmentioning

confidence: 99%

See 1 more Smart Citation

Pyramidal flux in an anisotropic diffusion scheme for enhancing structures in 3D images

et al. 2008

View full text Add to dashboard Cite

Pyramid based methods in image processing provide a helpful framework for accelerating the propagation of information over large spatial domains, increasing the efficiency for large scale applications. Combined with an anisotropic diffusion scheme tailored to preserve the boundaries at a given level, an efficient way for enhancing large structures in 3D images is presented. In our approach, the partial differential equation defining the evolution of the intensity in the image is solved in an explicit scheme at multiple resolutions in an ascending-descending cycle. Intensity 'flux' between distant voxels is allowed, while preserving borders relative to the scale. Experiments have been performed both with phantoms and with real data from 3D Transrectal Ultrasound Imaging. The effectiveness of the method to remove speckle noise and to enhance large structures such as the prostate has been demonstrated. For instance, using two scales reduces the computation time by 87% as compared to a single scale. Furthermore, we show that the boundaries of the prostate are mainly preserved, by comparing with manually outlined edges.

show abstract

Section: Introductionmentioning

confidence: 92%

Section: Flux Computation At a Single Level By F Lmentioning

confidence: 99%

Pyramidal flux in an anisotropic diffusion scheme for enhancing structures in 3D images

et al. 2008

View full text Add to dashboard Cite

show abstract

“…A structure-adaptive anisotropic filtering technique is proposed by Yang [11] for image filtering. We use a structure-adaptive anisotropic filter kernel proposed in [9] that has the following form: [9].…”

Section: Enhancement Using Anisotropic Filtermentioning

confidence: 99%

A chaincode based scheme for fingerprint feature extraction

Shi¹,

Govindaraju²

2006

Pattern Recognition Letters

View full text Add to dashboard Cite

Abstract. In this paper a fingerprint feature extraction algorithm for automatic fingerprint recognition is presented. The algorithm utilizes the well-known chaincode image representation in both of its image quality enhancement and fingerprint feature extraction. For its image enhancement a given fingerprint image is first binarized after a quick averaging to generate its chaincode representation. The direction field is estimated from a set of selected chaincodes. Then the original gray scale image is enhanced using a dynamic oriented filtering scheme together with the estimated direction field information. For its feature extraction, the enhanced fingerprint image is carefully binarized using a local-global binarization algorithm for generating the chaincode representation. Ridge selection is done based on a connected component analysis and finally the minutiae features are generated using a stroke following scheme.

show abstract

“…Despite its effectiveness in smoothing noise, the median filter tends to blur fine details and often destroys edges. In recent years, some modified median-based filters, such as weighted median (WM) filters [5,20,30,31,47] structure-adaptive anisotropic filters [16,46] and switching median filters [1,[9][10][11][12][13]22,26,27,33,[35][36][37]43,44] have been proposed to improve the median filter.…”

Section: Introductionmentioning

confidence: 99%

“…Steerable filters, in which a filter arbitrarily oriented is synthesized as a linear combination of a set of 'basis filters', have also been proposed [14]. Yang et al used local intensity orientation and an anisotropic measure to control the shapes of anisotropic filters [46]. Greenberg proposed an improved version of Yang's structured-adaptive filter [16].…”

Section: Introductionmentioning

confidence: 99%

A new adaptive center weighted median filter for suppressing impulsive noise in images

Lin

2007

Information Sciences

View full text Add to dashboard Cite

Structure adaptive anisotropic filtering

Cited by 19 publications

References 0 publications

Pyramidal flux in an anisotropic diffusion scheme for enhancing structures in 3D images

Pyramidal flux in an anisotropic diffusion scheme for enhancing structures in 3D images

A chaincode based scheme for fingerprint feature extraction

A new adaptive center weighted median filter for suppressing impulsive noise in images

Contact Info

Product

Resources

About