Scale-space from nonlinear filters

Bangham, Jenny; Ling, Paul D.; Harvey, Richard W.

doi:10.1109/iccv.1995.466791

Cited by 15 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar method, based on sequential alternating filters, has been proposed by Bangham and coworkers [3]. Their method is used on 1-D signals, though they discuss extensions to higher dimensions.…”

Section: Introductionmentioning

confidence: 99%

Morphological hat-transform scale spaces and their use in texture classification

Jalba

Roerdink

Wilkinson

Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)

View full text Add to dashboard Cite

In this paper we present a multi-scale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 % correct classification for the Brodatz texture database.

show abstract

Section: Introductionmentioning

confidence: 99%

Morphological hat-transform scale spaces and their use in texture classification

Jalba

Roerdink

Wilkinson

Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429)

View full text Add to dashboard Cite

show abstract

“…Bangham et al [22] show that discrete-domain 1-D sieve filtering satisfies the scalespace monotone requirement with edges as features. In this case, edges include any point not equal to the corresponding neighbor to the right.…”

Section: Connected Operators and Area Morphologymentioning

confidence: 99%

“…Scale-spaces may be generated by a number of different combinations of morphological operators. In the literature, previous studies have focused on those created by dilation or erosion [3], close or open [20,21], and close-open or open-close [22]. The dual of any operator that generates a scale-space generates another scale-space, or a dual scale-space.…”

Section: Background On Morphology and Morphological Scale-spacementioning

confidence: 99%

“…In 1-D, the open-close or close-open filters, using flat symmetric structuring elements, are equivalent to another class of non-linear filters called sieve filters [22], though this equivalence breaks down in higher dimension. Sieve filters can be extended to higher dimensions by interpreting them as connected operators, which act on the connected-components of the level-sets (see, for example, [26,27]).…”

Section: Connected Operators and Area Morphologymentioning

confidence: 99%

See 1 more Smart Citation

Morphological scale-space in image processing

Bosworth

Acton

2003

Digital Signal Processing

View full text Add to dashboard Cite

“…Multi-scale analysis is pivotal in both human and computer vision [1][2][3][4][5][6]. This is in part due to the fact that features of importance might be present at a range of scales, depending on distance to the observer or camera.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Parallel Algorithm for Multi-Scale Analysis of Connected Components in Gigapixel Images

Wilkinson

Pesaresi

Ouzounis³

2016

IJGI

View full text Add to dashboard Cite

Differential Morphological Profiles (DMPs) and their generalized Differential Attribute Profiles (DAPs) are spatial signatures used in the classification of earth observation data. The Characteristic-Salience-Leveling (CSL) is a model allowing the compression and storage of the multi-scale information contained in the DMPs and DAPs into raster data layers, used for further analytic purposes. Computing DMPs or DAPs is often constrained by the size of the input data and scene complexity. Addressing very high resolution remote sensing gigascale images, this paper presents a new concurrent algorithm based on the Max-Tree structure that allows the efficient computation of CSL. The algorithm extends the "one-pass" method for computation of DAPs, and delivers an attribute zone segmentation of the underlying trees. The DAP vector field and the set of multi-scale characteristics are computed separately and in a similar fashion to concurrent attribute filters. Experiments on test images of 3.48 to 3.96 Gpixel showed an average computational speed of 59.85 Mpixel per second, or 3.59 Gpixel per minute on a single 2U rack server with 64 opteron cores. The new algorithms could be extended to morphological keypoint detectors capable of handling gigascale images.

show abstract

Scale-space from nonlinear filters

Cited by 15 publications

References 23 publications

Morphological hat-transform scale spaces and their use in texture classification

Morphological hat-transform scale spaces and their use in texture classification

Morphological scale-space in image processing

An Efficient Parallel Algorithm for Multi-Scale Analysis of Connected Components in Gigapixel Images

Contact Info

Product

Resources

About