Local structure analyzers as determinants of preattentive pattern discrimination

Kröse, B.J.A.

doi:10.1007/bf02281975

Cited by 36 publications

(21 citation statements)

References 20 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent psychophysical experiments questioned the preattentive-attentive dichotomy and found graded discriminability in textures composed from randomly rotated patterns (similar to Figure 4) (Gurnsey and Browse 1987). Similar results were obtained in detection tasks (Krose 1987). They provide us with a database of discriminability measures for a set of randomly rotated arti cial pattern pairs.…”

Section: Models Of Texture Discrimination and Segmentationsupporting

confidence: 62%

“…The top and middle rows demonstrate textures composed of X-L and L-T patterns. These textures are widely studied (Julesz 1984;Gurnsey and Browse 1987;Krose 1987;Fogel and Sagi 1989;Malik and Perona 1990;Bergen and Adelson 1988) since the X-L texture is easily discriminated while the L-T requires more time and attention. This was measured (among other pattern pairs) by Gurnsey and Browse (Gurnsey and Browse 1987) and in detection tasks that yield similar results by Krose (Krose 1987).…”

Section: Discrimination Of Texture Micro-patterns By Generalized Symmmentioning

confidence: 99%

See 1 more Smart Citation

Quantification of local symmetry: application to texture discrimination

Bonneh¹,

Reisfeld²,

Yeshurun³

1994

Spatial Vis

View full text Add to dashboard Cite

Symmetry is one of the most prominent cues in visual perception as well as in computer vision. We have recently presented a Generalized Symmetry Transform that receives as input an edge map, and outputs a symmetry map, where every point marks the intensity and orientation of the local generalized symmetry. In the context of computer vision, this map emphasizes points of high symmetry, which, in turn, are used to detect regions of interest for active vision systems. Many psychophysical experiments in texture discrimination use images that consist of various micro-patterns. Since the Generalized Symmetry Transform captures local spatial relations between image edges, it has been used here to predict human performance in discrimination tasks. Applying the transform to micro-patterns in some well-studied quantitative experiments of human texture discrimination, it is shown that symmetry, as characterized by the present computational scheme, can account for most of them.

show abstract

Section: Models Of Texture Discrimination and Segmentationsupporting

confidence: 62%

Section: Discrimination Of Texture Micro-patterns By Generalized Symmmentioning

confidence: 99%

Quantification of local symmetry: application to texture discrimination

Bonneh¹,

Reisfeld²,

Yeshurun³

1994

Spatial Vis

View full text Add to dashboard Cite

show abstract

“…Note, that a classification rate of 90% is almost perfect for these examples, since border effects cause a classification error of about 10% as can be seen in Figure 13(h). The rank order of discriminability for the CLM model matches the data from (Kröse, 1987) remarkably well and we therefore conclude that the CLM texture model also resembles human texture perception from a quantitive point of view. …”

Section: Comparison To Psychophysical Datasupporting

confidence: 61%

“…In order to give a quantitive comparison of our model's performance with human data, we have constructed a set of texture pairs according to (Kröse, 1987). The images used for the benchmark are shown in Figure 13.…”

Section: Comparison To Psychophysical Datamentioning

confidence: 99%

A computational feature binding model of human texture perception

Ontrup

Wersing²,

Ritter

2004

Cognitive Processing

View full text Add to dashboard Cite

We present a computational model for human texture perception which assigns functional principles to the Gestalt laws of similarity and proximity. Motivated by early vision mechanisms, in a first step local texture features are extracted by utilizing multi-scale filtering and non-linear spatial pooling. In the second stage, features are grouped according to the spatial feature binding model of the Competitive Layer Model (CLM) (Wersing, Steil, & Ritter, 2001). The CLM uses cooperative and competitive interactions in a recurrent network, where binding is expressed by the layer-wise coactivation of feature-representing neurons. The Gestalt law of similarity is expressed by a non-euclidean distance measure in the abstract feature space with proximity being taken into account by a spatial component. To choose the stimulus dimensions which allow the most salient similarity-based texture segmentation, the feature similarity metrics is reduced to the directions of maximum variance. We show that our combined texture feature extraction and binding model performs segmentation in strong conformity with human perception. The examples range from classical microtextures and Brodatz textures to other classical Gestalt stimuli, which offer a new perspective on the role of texture for more abstract similarity grouping.

show abstract

“…There are primarily two classes of texture analysis approaches. They are: (i) spatial domain [13] , and (ii) transform-domain [14,15] approaches. Therefore one can utilize quantitative descriptors for texture properties as the building blocks for deriving the image clutter measure.…”

Section: Texture-based Image Clutter Measuresmentioning

confidence: 99%

<title>Quantitative characterization of image clutter: problem, progress, and promises</title>

Trivedi

Shirvaikar

1993

SPIE Proceedings

View full text Add to dashboard Cite

In this paper we present an overview of research studies aimed at deriving quantitative measures for image clutter. Image clutter is identified as a perceptual effect and therefore quantitative measures for clutter should be derived on the basis of models for perception. Previous studies in the field have produced limited success since they concentrated on the signal level interpretation in clutter characterization. In this study, we promote examination of the clutter problem at a higher level, where preattentive cues form the basis for their definition. Specifically, we derive clutter measures based upon preattentive texture features. Results of an extensive experimental study highlight the limitations of signal level clutter measures and the utility of texture based measures.

show abstract

Local structure analyzers as determinants of preattentive pattern discrimination

Cited by 36 publications

References 20 publications

Quantification of local symmetry: application to texture discrimination

Quantification of local symmetry: application to texture discrimination

A computational feature binding model of human texture perception

<title>Quantitative characterization of image clutter: problem, progress, and promises</title>

Contact Info

Product

Resources

About