Statistics and category systems for the shape index descriptor of local 2nd order natural image structure

Lillholm, Martin; Griffin, Lewis D.

doi:10.1016/j.imavis.2008.08.003

Cited by 10 publications

(17 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apparently there is something special the case with the saddle category. It is unlikely to be a prior, because saddles are actually more frequent in nature than caps or cups (Koenderink & van Doorn, 2003; Lillholm & Griffin, 2007). …”

Section: Discussionmentioning

confidence: 99%

Local Shape of Pictorial Relief

2014

View full text Add to dashboard Cite

How is pictorial relief represented in visual awareness? Certainly not as a “depth map,” but perhaps as a map of local surface attitudes (Koenderink & van Doorn, 1995). Here we consider the possibility that observers might instead, or concurrently, represent local surface shape, a geometrical invariant with respect to motions. Observers judge local surface shape, in a picture of a piece of sculpture, on a five-point categorical scale. Categories are cap–ridge–saddle–rut–cup–flat, where “flat” denotes the absence of shape. We find that observers readily perform such a task, with full resolution of a shape index scale (cap–ridge–saddle–rut–cup), and with excellent self-consistency over days. There exist remarkable inter-observer differences. Over a group of 10 naive observers we find that the dispersion of judgments peaks at the saddle category. There may be a relation of this finding to the history of the topic—Alberti's (1827) omission of the saddle category in his purportedly exhaustive catalog of local surface shapes.

show abstract

Section: Discussionmentioning

confidence: 99%

Local Shape of Pictorial Relief

2014

View full text Add to dashboard Cite

show abstract

“…The novelty in our classification method consists of a texture descriptor based on second-order image structure captured by the shape index [2], [3]. We summarize the statistics of the shape index in histograms using a new pooling scheme consisting of concentric donut-shaped rings centered on the cell.…”

Section: Ndirect Immunofluorescence (Iff) Of Human Epithelialmentioning

confidence: 99%

“…We compute the differential structure of the image from the normalized scale space derivatives (3) where and indicate the order of the differential along the and axis, respectively. For notational convenience we omit the arguments and substitute with simply .…”

Section: A Differential Image Structurementioning

confidence: 99%

See 1 more Smart Citation

HEp-2 Cell Classification Using Shape Index Histograms With Donut-Shaped Spatial Pooling

Larsen

Vestergaard

Larsen

2014

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

We present a new method for automatic classification of indirect immunoflourescence images of HEp-2 cells into different staining pattern classes. Our method is based on a new texture measure called shape index histograms that captures second-order image structure at multiple scales. Moreover, we introduce a spatial decomposition scheme which is radially symmetric and suitable for cell images. The spatial decomposition is performed using donut-shaped pooling regions of varying sizes when gathering histogram contributions. We evaluate our method using both the ICIP 2013 and the ICPR 2012 competition datasets. Our results show that shape index histograms are superior to other popular texture descriptors for HEp-2 cell classification. Moreover, when comparing to other automated systems for HEp-2 cell classification we show that shape index histograms are very competitive; especially considering the relatively low complexity of the method.

show abstract

“…A prior for the shape index can be obtained from first principles (Koenderink and van Doorn, 2003b;Lillholm and Griffin, 2009), for instance one might use the distribution of shape indices for isotropic random Gaussian surfaces. One finds…”

Section: Local Shape Inferencementioning

confidence: 99%

Shading, a View from the Inside

Koenderink¹,

Doorn²,

Pont³

2012

Seeing and Perceiving

View full text Add to dashboard Cite

Shape from shading arose from artistic practice, and later experimental psychology, but its formal structure has only been established recently by computer vision. Some of its algorithms have led to useful applications. Psychology has reversely borrowed these formalisms in attempts to come to grips with shading as a depth cue. Results have been less than spectacular. The reason might well be that these formalisms are all based on Euclidean geometry and physics (radiometry), which, are the right tools in third person accounts, but have little relevance to first person accounts, and thus are biologically (and consequently psychologically) of minor interest. We propose a formal theory of the shading cue in the first person account, 'a view from the inside'. Such a perspective is also required for autonomous robots in AI. This formalism cannot be based on Euclidean geometry, nor on radiometry, but on the structure of pictorial space, and the structure of brightness space. The formalism, though different in kind, has a simple relation to the computer vision accounts. It has great robustness, is free from calibration issues, and allows purely local shape inferences. It is especially suited to biological (and thus AI) implementation. We consider a number of predictions and confront them with available empirical evidence.

show abstract

Statistics and category systems for the shape index descriptor of local 2nd order natural image structure

Cited by 10 publications

References 52 publications

Local Shape of Pictorial Relief

Local Shape of Pictorial Relief

HEp-2 Cell Classification Using Shape Index Histograms With Donut-Shaped Spatial Pooling

Shading, a View from the Inside

Contact Info

Product

Resources

About