https://scholars.lib.ntu.edu.tw/handle/123456789/576180
Title: | A Novel Feature Detection Method Using Multi-Dimensional Image Fusion for Automated Optical Inspection on Critical Dimension [適用於關鍵尺寸自動光學檢測的創新多維融合圖像特徵偵測方法] | Authors: | Chen L.-C Liang C.-W Hoang D.-C Duong D.-H Chen C.-S Lin S.-T. LIANG-CHIA CHEN |
Keywords: | Edge detection; Feature extraction; Image segmentation; Optical data processing; Optical testing; Aerospace composites; Automated optical inspection; Critical dimension; Critical dimension measurement; Measurement repeatability; Multi-dimensional images; Object segmentation; Point cloud; Image fusion | Issue Date: | 2018 | Journal Volume: | 39 | Journal Issue: | 2 | Start page/Pages: | 145-152 | Source: | Journal of the Chinese Society of Mechanical Engineers, Transactions of the Chinese Institute of Engineers, Series C/Chung-Kuo Chi Hsueh Kung Ch'eng Hsuebo Pao | Abstract: | This paper presents a novelapproach which is based on multi-dimension image fusion to effective extraction and segmentation of edge features foraccurately measuring critical dimension on objects having complicated surface patternsor random reflectance.In the approach, coarse estimation of edge points is firstlyperformed by usingthe 3D edge detector to identifycorrect image regions of interest(ROI)for object segmentation. 2D image processing algorithms are performed on the ROI tosegment the preciseobject edges for critical dimension (CD) measurement. To verify the effectiveness of the strategy, the developed method has been verified through measurement of aerospace composite parts for its edge detection and critical dimension accuracy.The measurement repeatability error of this critical dimension can be kept below1.1% of the measured CD while the standard deviation can be kept less than 0.137 mm.Experimental results have demonstrated the feasibility and applicability of the developed method. ? 2018, Chinese Mechanical Engineering Society. All right reserved. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059863197&partnerID=40&md5=aca1f4bf042b83eb920a6ce28e21a87a https://scholars.lib.ntu.edu.tw/handle/123456789/576180 |
ISSN: | 2579731 |
Appears in Collections: | 機械工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.