Active Contours Driven by Supervised Binary Classifiers for Texture Segmentation

Olivier, Julien; Boné, Romuald; Rousselle, Jean-Jacques; Cardot, Hubert

doi:10.1007/978-3-540-89639-5_28

Cited by 6 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…in [9]. Since then, much research has been carried out and many extensions and variations have been proposed for numerous applications such as image segmentation and visual tracking [21], [20], [5], [4], [8], [7], [3], [15], [16], [17], [18], [15].…”

Section: A Active Contours: a Variational Segmentation Frameworkmentioning

confidence: 99%

Towards stabilizing parametric active contours

Liu

Fan

Olsen

et al. 2014

The 4th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent

View full text Add to dashboard Cite

Numerical instability often occurs in evolving of parametric active contours. This is mainly due to the undesired change of parametrization during evolution. In this paper, we propose a new tangential diffusion term to compensate this undesired change. As a result, the parametrization will converge to a parametrization that is proportional to the natural parametrization which implies that the control points of the contour are uniformly distributed. We theoretically prove that this tangential diffusion term is bounded and therefore numerically stable. Several experiments were conducted and verified the feasibility of the proposed tangential diffusion force.

show abstract

Section: A Active Contours: a Variational Segmentation Frameworkmentioning

confidence: 99%

Towards stabilizing parametric active contours

Liu

Fan

Olsen

et al. 2014

The 4th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent

View full text Add to dashboard Cite

show abstract

“…In [9], [10] and [11], the concepts of region-based forces arising from the statistical modelling of different regions have been suggested. In [12], the authors proposed an active contour driven explicitly by supervised binary classifiers, more specifically a k-nearest neighbourhood, a support vector machine and a neural network. For each pixel, Haralick features were computed and used as the input of classifiers.…”

Section: B the Weld Pool Boundary Tracking Algorithmmentioning

confidence: 99%

A real-time passive vision system for robotic arc welding

Liu

Fan²,

Olsen

et al. 2015

2015 IEEE International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

Visual sensing in arc welding has become more and more important. However, it has remained a challenging problem due to the harsh environment, especially the interference of the extremely strong arc light. A typical industrial solution for seam detection is to use laser scanner which however still suffers from several limitations. Solutions for weld pool sensing mostly rely on high speed cameras and powerful external illuminations and therefore the wide use in industrial environments is limited. In this paper we present a real-time passive machine vision system for both seam tracking and weld pool sensing in robotic arc welding. The system, which consists of a CCD camera and a carefully-selected narrowband pass filter, is capable of extracting the geometrical profile of the seam that is close to the arc region and the weld pool boundary simultaneously in real time. This visual information can be further utilized by the control system to navigate the welding robot and adjust the welding parameters. Experiments including several real-time demonstrations have been made and verified the feasibility of the proposed vision system.

show abstract

“…The next section presents the principle of supervised binary classification. Details about the introduction of the classifier in the motion equation can be found in (Olivier et al (2008)). …”

Section: Active Contour Segmentationmentioning

confidence: 99%