An Elastic Net Learning Algorithm for Edge Linking of Images

Jiahai WANG; Zheng TANG; Qiping CAO; Xinshun XU

An Elastic Net Learning Algorithm for Edge Linking of Images

Jiahai WANG, Zheng TANG, Qiping CAO, Xinshun XU

Full Text Views

0

Cite this

Summary :

Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed as a constrained optimization problem, it is NP hard-being isomorphic to the classical Traveling Salesman Problem. This paper proposes a gradient ascent learning algorithm of the elastic net approach for edge linking of images. The learning algorithm has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase minimizes the path through the edge points. The procedure is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are repeated until the elastic net gets out of local minima and produces the shortest or better contour through edge points. We test the algorithm on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and producing more meaningful contours than the original elastic net.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.11 pp.2879-2886

Publication Date: 2003/11/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Neural Networks and Bioengineering

Cite this

Copy

Jiahai WANG, Zheng TANG, Qiping CAO, Xinshun XU, "An Elastic Net Learning Algorithm for Edge Linking of Images" in IEICE TRANSACTIONS on Fundamentals, vol. E86-A, no. 11, pp. 2879-2886, November 2003, doi: .
Abstract: Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed as a constrained optimization problem, it is NP hard-being isomorphic to the classical Traveling Salesman Problem. This paper proposes a gradient ascent learning algorithm of the elastic net approach for edge linking of images. The learning algorithm has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase minimizes the path through the edge points. The procedure is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are repeated until the elastic net gets out of local minima and produces the shortest or better contour through edge points. We test the algorithm on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and producing more meaningful contours than the original elastic net.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e86-a_11_2879/_p

Copy

@ARTICLE{e86-a_11_2879,
author={Jiahai WANG, Zheng TANG, Qiping CAO, Xinshun XU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Elastic Net Learning Algorithm for Edge Linking of Images},
year={2003},
volume={E86-A},
number={11},
pages={2879-2886},
abstract={Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed as a constrained optimization problem, it is NP hard-being isomorphic to the classical Traveling Salesman Problem. This paper proposes a gradient ascent learning algorithm of the elastic net approach for edge linking of images. The learning algorithm has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase minimizes the path through the edge points. The procedure is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are repeated until the elastic net gets out of local minima and produces the shortest or better contour through edge points. We test the algorithm on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and producing more meaningful contours than the original elastic net.},
keywords={},
doi={},
ISSN={},
month={November},}

Copy

TY - JOUR
TI - An Elastic Net Learning Algorithm for Edge Linking of Images
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2879
EP - 2886
AU - Jiahai WANG
AU - Zheng TANG
AU - Qiping CAO
AU - Xinshun XU
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2003
AB - Edge linking is a fundamental computer vision task, yet presents difficulties arising from the lack of information in the image. Viewed as a constrained optimization problem, it is NP hard-being isomorphic to the classical Traveling Salesman Problem. This paper proposes a gradient ascent learning algorithm of the elastic net approach for edge linking of images. The learning algorithm has two phases: an elastic net phase, and a gradient ascent phase. The elastic net phase minimizes the path through the edge points. The procedure is equivalent to gradient descent of an energy function, and leads to a local minimum of energy that represents a good solution to the problem. Once the elastic net gets stuck in local minima, the gradient ascent phase attempts to fill up the valley by modifying parameters in a gradient ascent direction of the energy function. Thus, these two phases are repeated until the elastic net gets out of local minima and produces the shortest or better contour through edge points. We test the algorithm on a set of artificial images devised with the aim of demonstrating the sort of features that may occur in real images. For all problems, the systems are shown to be capable of escaping from the elastic net local minima and producing more meaningful contours than the original elastic net.
ER -