Two methods of random seed generation to avoid over‐segmentation with stochastic watershed: application to nuclear fuel micrographs

Tolosa, S. Cativa; Blacher, Silvia; Denis, Anne; Marajofsky, A.; Pirard, Jean‐Paul; Gommes, Cédric

doi:10.1111/j.1365-2818.2009.03200.x

Cited by 8 publications

(3 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea is that if a number of markers, ideally greater than the number of regions, are placed at random on the image to be segmented, the results will be a combination of true and spurious watershed lines; by repeating the experiment a number of times, true lines will appear far more often than each of the individual spurious lines, thus enabling to determine a probability density function of the watershed lines by averaging the results of the experiments. However, this algorithm still requires the user to determine the number of relevant regions, careful tuning of the distribution used to generate random seeds [45], and does not cope well with leaky region boundaries such as the one depicted in Fig. 9.…”

Section: Classical Watershed Segmentationmentioning

confidence: 99%

Soccer line mark segmentation and classification with stochastic watershed transform

Berjón¹,

Cuevas²,

García³

2021

Preprint

View full text Add to dashboard Cite

Augmented reality applications are beginning to change the way sports are broadcast, providing richer experiences and valuable insights to fans. The first step of augmented reality systems is camera calibration, possibly based on detecting the line markings of the field of play. Most existing proposals for line detection rely on edge detection and Hough transform, but optical distortion and extraneous edges cause inaccurate or spurious detections of line markings. We propose a novel strategy to automatically and accurately segment line markings based on a stochastic watershed transform that is robust to optical distortions, since it makes no assumptions about line straightness, and is unaffected by the presence of players or the ball in the field of play. Firstly, the playing field as a whole is segmented completely eliminating the stands and perimeter boards. Then the line markings are extracted.The strategy has been tested on a new and public database composed by 60 annotated images from matches in five stadiums. The results obtained have proven that the proposed segmentation algorithm allows successful and precise detection of most line mark pixels.

show abstract

Section: Classical Watershed Segmentationmentioning

confidence: 99%

Soccer line mark segmentation and classification with stochastic watershed transform

Berjón¹,

Cuevas²,

García³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Campbell et al (Ref 33), for instance, used it to differentiate phases in titanium alloys. In order to apply this tool to this particular problem, it is first necessary to perform a distance transform (Ref 34,35) to the complement of the binary image. This transformation assigns to each pixel of a carbide a number that is equal to its distance to the nearest pixel belonging to a different phase.…”

Section: Conversion Of the Mesoscale Micrographs Into Binary Imagesmentioning

confidence: 99%

Microstructural Analysis of Powder Metallurgy Tool Steels in the Context of Abrasive Wear Behavior: A New Computerized Approach to Stereology

Benito

Wulbieter

Pöhl

et al. 2019

J. of Materi Eng and Perform

View full text Add to dashboard Cite

The present work describes a new methodology designed to characterize the microstructures of tool steels containing carbide hard phases, with the focus set on their abrasive wear resistance. A series of algorithms were designed and implemented in MATLABÒ to (i) recognize each of the features of interest, (ii) measure relevant quantities and (iii) characterize each of the phases and the alloy in function of attributes usually neglected in wear description applications: size distribution, shape and contiguity of the hard phases. The new framework incorporates new parameters to describe each one of these attributes, as observed in SEM micrographs. All three aforementioned stages contain novel contributions that can be potentially beneficial to the field of materials design in general and to the field of alloy design for severely abrasive environments in particular. Models of known geometry and micrographs of different powder metallurgy steels were analyzed, and the obtained results were compared with the obtained by the linear intercept method. The relation between the new parameters and the ones available in the scientific literature is also discussed.

show abstract

“…Hence to come up with the final result, the most dominant watershed lines have to be extracted from the intensity map, wherefore several possibilities are proposed in Faessel and Jeulin (2010). Further developments on this segmentation technique are discussed in Cativa Tolosa et al (2009), where the placement of the markers is more specific to avoid an over-segmentation of the data.…”

Section: Stochastic Representationmentioning

confidence: 99%

A Multiscale Approach to the Representation of 3d Images, With Application to Polymer Solar Cells

Thiedmann¹,

Hassfeld²,

Stenzel³

et al. 2011

Image Anal Stereol

View full text Add to dashboard Cite

A multiscale approach to the description of geometrically complex 3D image data is proposed which distinguishes between morphological features on a 'macro-scale' and a 'micro-scale'. Since our method is mainly tailored to nanostructures observed in composite materials consisting of two different phases, an appropriate binarization of grayscale images is required first. Then, a morphological smoothing is applied to extract the structural information from binarized image data on the 'macro-scale'. A stochastic algorithm is developed for the morphologically smoothed images whose goal is to find a suitable representation of the macro-scale structure by unions of overlapping spheres. Such representations can be interpreted as marked point patterns. They lead to an enormous reduction of data and allow the application of well-known tools from point-process theory for their analysis and structural modeling. All those voxels which have been 'misspecified' by the morphological smoothing and subsequent representation by unions of overlapping spheres are interpreted as 'micro-scale' structure. The exemplary data sets considered in this paper are 3D grayscale images of photoactive layers in hybrid solar cells gained by electron tomography. These composite materials consist of two phases: a polymer phase and a zinc oxide phase. The macro-scale structure of the latter is represented by unions of overlapping spheres.

show abstract

Two methods of random seed generation to avoid over‐segmentation with stochastic watershed: application to nuclear fuel micrographs

Cited by 8 publications

References 9 publications

Soccer line mark segmentation and classification with stochastic watershed transform

Soccer line mark segmentation and classification with stochastic watershed transform

Microstructural Analysis of Powder Metallurgy Tool Steels in the Context of Abrasive Wear Behavior: A New Computerized Approach to Stereology

A Multiscale Approach to the Representation of 3d Images, With Application to Polymer Solar Cells

Contact Info

Product

Resources

About