Object Descriptors Based on a List of Rectangles: Method and Algorithm

Droogenbroeck, Marc Van; Pierard, Sébastien

doi:10.1007/978-3-642-21569-8_14

Cited by 3 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…holes, which reduces the object). The CBR of the shape is very sensitive to negative noise (as a single pixel wide hole can potentially disturb the whole set of rectangles) but nearly insensitive to positive noise (stains only add a few rectangles to the CBR, and the number of added rectangles is bounded by the area of the stains, as proven by Van Droogenbroeck et al [30]). For the CBR of the inverse shape, it is the contrary.…”

Section: Propertiesmentioning

confidence: 99%

See 2 more Smart Citations

Boosting Shape Classifiers Accuracy by Considering the Inverse Shape

Pierard¹,

Lejeune²,

Droogenbroeck³

2016

JPRR

Self Cite

View full text Add to dashboard Cite

Many techniques exist for describing shapes. These techniques almost exclusively consider the contour or the inside of the shape; the major problem for describing the outside of a shape, or inverse shape, being that it has an infinite extension. In this paper, we show how to adapt two shape descriptors , one region based, the Cover By Rectangles, and one transform based, the Zernike moments, to be applicable to the inverse shape. We analyze their properties, and show how to deal with the infinite extension of the inverse shape. Then, we apply these descriptors to shape classification and compare representations that use the shape, its inverse, or both. Our experiments establish that, for shape classification, a representation integrating the inverse shape often outperforms a representation restricted to the shape. This opens the path for better techniques that could use, as a rule of thumb, both the representations of a shape and its inverse for the purpose of classification.

show abstract

Section: Propertiesmentioning

confidence: 99%

“…As shown in [30], the CBR is a fast to compute region-based descriptor; it is thus appropriate for real-time applications.…”

Section: Shape Representationmentioning

confidence: 99%

See 1 more Smart Citation

Boosting Shape Classifiers Accuracy by Considering the Inverse Shape

Pierard¹,

Lejeune²,

Droogenbroeck³

2016

JPRR

Self Cite

View full text Add to dashboard Cite

show abstract

“…of the elements. We use an efficient maximal empty rectangles algorithm [39] to find places in this array where we can move or grow elements to modify the layout. Additionally, each element also has an internal array representing the positions of any child elements relative to itself.…”

Section: Definition: Layout Design Taskmentioning

confidence: 99%

Sketchplore

Todi

Weir

Oulasvirta

2016

Proceedings of the 2016 ACM Conference on Designing Interactive Systems

View full text Add to dashboard Cite

Real-Time Optimisation Sketchploration Environment Figure 1: Sketchplorer is an interactive layout sketching tool supported by real-time model-based optimisation. The tool is designed to facilitate the creative and problem-solving aspects of sketching without requiring extensive input. While a designer is sketching, a design task is automatically inferred. The optimiser uses predictive models to make suggestions for local and global changes that improve usability and aesthetics. Suggestions appear on the side, and never override the designer's work.

show abstract

Selection in a 3D microtomographic image the region with the highest quality

Kornilov

Safonov

Goncharova³

et al. 2019

Proceedings of the v International Conference Information Technology and Nanotechnology 2019

View full text Add to dashboard Cite

We present an algorithm for processing of X-ray microtomographic (micro-CT) images that allows automatic selection of a sub-volume having the best visual quality for further mathematical simulation, for example, flow simulation. Frequently, an investigated sample occupies only a part of a volumetric image or the sample can be into a holder; a part of the image can be cropped. For each 2D slice across the Z-axis of an image, the proposed method locates a region corresponding to the sample. We explored applications of several existing blind quality measures for an estimation of the visual quality of a micro-CT image slice. Some of these metrics can be applied to ranking the image regions according to their quality. Our method searches for a cubic area located inside regions belonging to the sample and providing the maximal sum of the quality measures of slices crossing the cube across the Z-axis. The proposed technique was tested on synthetic and real micro-CT images of rocks.

show abstract

Object Descriptors Based on a List of Rectangles: Method and Algorithm

Cited by 3 publications

References 7 publications

Boosting Shape Classifiers Accuracy by Considering the Inverse Shape

Boosting Shape Classifiers Accuracy by Considering the Inverse Shape

Sketchplore

Selection in a 3D microtomographic image the region with the highest quality

Contact Info

Product

Resources

About