Using entropy based mean shift filter and modified watershed transform for grain segmentation

Kun Zhang, Minrui Fei, Huiyu Zhou

Research output: Contribution to journalArticle

245 Downloads (Pure)

Abstract

Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper,we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice.However,due to the over-segmentation issue,this technique has experienced poor performance in various applications,such as inhomogeneous background and connected targets. To solve this problem,we present a combination of two classical techniques to handle this issue.In the first step,a mean shift filter is used to eliminate the inhomogeneous background, where entropy is used to be a converging criterion. Secondly,a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.
Original languageEnglish
Pages (from-to)199-207
Number of pages9
JournalInternational Journal of Automation and Computing
Volume12
Issue number2
Early online date11 Mar 2015
DOIs
Publication statusPublished - Apr 2015

Fingerprint

Mean Shift
Watersheds
Entropy
Segmentation
Transform
Filter
Food safety
Processing
Image processing
Life sciences
Gradient Algorithm
Color
Usability
Execution Time
Image Processing
Eliminate
Die
Safety
Ring
Target

Cite this

@article{31321e97a8eb4991b810a34999248cb2,
title = "Using entropy based mean shift filter and modified watershed transform for grain segmentation",
abstract = "Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper,we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice.However,due to the over-segmentation issue,this technique has experienced poor performance in various applications,such as inhomogeneous background and connected targets. To solve this problem,we present a combination of two classical techniques to handle this issue.In the first step,a mean shift filter is used to eliminate the inhomogeneous background, where entropy is used to be a converging criterion. Secondly,a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.",
author = "Kun Zhang and Minrui Fei and Huiyu Zhou",
year = "2015",
month = "4",
doi = "10.1007/s11633-014-0841-2",
language = "English",
volume = "12",
pages = "199--207",
journal = "International Journal of Automation and Computing",
issn = "1476-8186",
publisher = "Chinese Academy of Sciences",
number = "2",

}

Using entropy based mean shift filter and modified watershed transform for grain segmentation. / Zhang, Kun; Fei, Minrui; Zhou, Huiyu.

In: International Journal of Automation and Computing, Vol. 12, No. 2, 04.2015, p. 199-207.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Using entropy based mean shift filter and modified watershed transform for grain segmentation

AU - Zhang, Kun

AU - Fei, Minrui

AU - Zhou, Huiyu

PY - 2015/4

Y1 - 2015/4

N2 - Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper,we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice.However,due to the over-segmentation issue,this technique has experienced poor performance in various applications,such as inhomogeneous background and connected targets. To solve this problem,we present a combination of two classical techniques to handle this issue.In the first step,a mean shift filter is used to eliminate the inhomogeneous background, where entropy is used to be a converging criterion. Secondly,a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.

AB - Life science research aims to continuously improve the quality and standard of human life. One of the major challenges in this area is to maintain food safety and security. A number of image processing techniques have been used to investigate the quality of food products. In this paper,we propose a new algorithm to effectively segment connected grains so that each of them can be inspected in a later processing stage. One family of the existing segmentation methods is based on the idea of watersheding, and it has shown promising results in practice.However,due to the over-segmentation issue,this technique has experienced poor performance in various applications,such as inhomogeneous background and connected targets. To solve this problem,we present a combination of two classical techniques to handle this issue.In the first step,a mean shift filter is used to eliminate the inhomogeneous background, where entropy is used to be a converging criterion. Secondly,a color gradient algorithm is used in order to detect the most significant edges, and a marked watershed transform is applied to segment cluttered objects out of the previous processing stages. The proposed framework is capable of compromising among execution time, usability, efficiency and segmentation outcome in analyzing ring die pellets. The experimental results demonstrate that the proposed approach is effectiveness and robust.

U2 - 10.1007/s11633-014-0841-2

DO - 10.1007/s11633-014-0841-2

M3 - Article

VL - 12

SP - 199

EP - 207

JO - International Journal of Automation and Computing

JF - International Journal of Automation and Computing

SN - 1476-8186

IS - 2

ER -