Feature Extraction for Structured Surface Based on Surface Networks and Edge Detection

L. Blunt, P. Scott, X. Jiang, S. Xiao, F. Xie

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper presents a novel morphological feature extraction technique in which networks of structured surfaces are built on the basis of the edge information of a measured surface. These networks contain all the surface geometrical patterns and these are categorised into the individual feature primitives such as the hill/dale, peak, pit and saddle point. Furthermore, the connections between these features are also constructed in the network, so height and area pruning methods of surface networks enable the combination and removal of insignificant features flexibly and effectively on the basis of their network connections. The proposed morph-edge method can effectively separate various surface regions with complicated overlapping and indistinct boundaries. This morph-edge surface segmentation technique is presented and discussed in the light of practical applications to structured surface analysis.

LanguageEnglish
Pages210-214
Number of pages5
JournalMaterials Science in Semiconductor Processing
Volume9
Issue number1-3
DOIs
Publication statusPublished - 1 Feb 2006

Fingerprint

edge detection
Edge detection
pattern recognition
Feature extraction
Surface analysis
saddle points

Cite this

@article{c070670d53f24e01b1b8915e65ee752c,
title = "Feature Extraction for Structured Surface Based on Surface Networks and Edge Detection",
abstract = "This paper presents a novel morphological feature extraction technique in which networks of structured surfaces are built on the basis of the edge information of a measured surface. These networks contain all the surface geometrical patterns and these are categorised into the individual feature primitives such as the hill/dale, peak, pit and saddle point. Furthermore, the connections between these features are also constructed in the network, so height and area pruning methods of surface networks enable the combination and removal of insignificant features flexibly and effectively on the basis of their network connections. The proposed morph-edge method can effectively separate various surface regions with complicated overlapping and indistinct boundaries. This morph-edge surface segmentation technique is presented and discussed in the light of practical applications to structured surface analysis.",
keywords = "Edge Detection, Morphological Feature, Surface Network, Surface Segmentation",
author = "L. Blunt and P. Scott and X. Jiang and S. Xiao and F. Xie",
year = "2006",
month = "2",
day = "1",
doi = "10.1016/j.mssp.2006.01.085",
language = "English",
volume = "9",
pages = "210--214",
journal = "Materials Science in Semiconductor Processing",
issn = "1369-8001",
publisher = "Elsevier Limited",
number = "1-3",

}

Feature Extraction for Structured Surface Based on Surface Networks and Edge Detection. / Blunt, L.; Scott, P.; Jiang, X.; Xiao, S.; Xie, F.

In: Materials Science in Semiconductor Processing, Vol. 9, No. 1-3, 01.02.2006, p. 210-214.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Feature Extraction for Structured Surface Based on Surface Networks and Edge Detection

AU - Blunt, L.

AU - Scott, P.

AU - Jiang, X.

AU - Xiao, S.

AU - Xie, F.

PY - 2006/2/1

Y1 - 2006/2/1

N2 - This paper presents a novel morphological feature extraction technique in which networks of structured surfaces are built on the basis of the edge information of a measured surface. These networks contain all the surface geometrical patterns and these are categorised into the individual feature primitives such as the hill/dale, peak, pit and saddle point. Furthermore, the connections between these features are also constructed in the network, so height and area pruning methods of surface networks enable the combination and removal of insignificant features flexibly and effectively on the basis of their network connections. The proposed morph-edge method can effectively separate various surface regions with complicated overlapping and indistinct boundaries. This morph-edge surface segmentation technique is presented and discussed in the light of practical applications to structured surface analysis.

AB - This paper presents a novel morphological feature extraction technique in which networks of structured surfaces are built on the basis of the edge information of a measured surface. These networks contain all the surface geometrical patterns and these are categorised into the individual feature primitives such as the hill/dale, peak, pit and saddle point. Furthermore, the connections between these features are also constructed in the network, so height and area pruning methods of surface networks enable the combination and removal of insignificant features flexibly and effectively on the basis of their network connections. The proposed morph-edge method can effectively separate various surface regions with complicated overlapping and indistinct boundaries. This morph-edge surface segmentation technique is presented and discussed in the light of practical applications to structured surface analysis.

KW - Edge Detection

KW - Morphological Feature

KW - Surface Network

KW - Surface Segmentation

UR - http://www.scopus.com/inward/record.url?scp=33744541303&partnerID=8YFLogxK

U2 - 10.1016/j.mssp.2006.01.085

DO - 10.1016/j.mssp.2006.01.085

M3 - Article

VL - 9

SP - 210

EP - 214

JO - Materials Science in Semiconductor Processing

T2 - Materials Science in Semiconductor Processing

JF - Materials Science in Semiconductor Processing

SN - 1369-8001

IS - 1-3

ER -