English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28603/40634
Visitors : 4343228      Online Users : 252
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/40808

Title: Profiles Detection in Ring Convex Forming by ACLN with Sub-Pixel Accuracy
Authors: Jang-Ping Wang;Guo-Ming Huang;Sheng-Hua Yurs
Contributors: 國立臺灣海洋大學:輪機工程學系
Keywords: Ring test;Adaptive competitive learning network;Sub-pixel accuracy
Date: 2008
Issue Date: 2017-02-07T01:16:25Z
Publisher: Key Engineering Materials
Abstract: Abstract:An optical measuring system for the ring test is proposed. In this approach, the machine vision inspection equipment is first built to record and capture the images of ring test from the digital camcorder.The image processing procedures to detect and locate the edge points of the inner and outer radii in ring convex forming are presented. Unlike the conventional sub-pixel estimation based on gray-level values, the quantity (8 bits) of color’s scale has been adopted. In image processing procedures, a clustering method called Adaptive Competitive Learning Network (ACLN) is first used to classify the image hues which represent the different heights of bulge profiles on the top of ring, and then the edge points can be searched by the interpolation step of subpixel accuracy. The calibration curves constructed by the mode of non-constant friction factor called F-value approach is designed to compare and check with the measurement data. The experimental results will be presented and discussed in this study.
Relation: 364-366, pp.199-204
URI: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/40808
Appears in Collections:[輪機工程學系] 期刊論文

Files in This Item:

File Description SizeFormat PDF32View/Open

All items in NTOUR are protected by copyright, with all rights reserved.


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback