Thresholding-based detection of fine and sparse details
Thresholding-based detection of fine and sparse details作者机构：Machine Vision and Pattern Recognition LaboratoryDepartment of Information TechnologyFaculty of Technology ManagementLappeenranta University of TechnologyP.O.Box 20FI-53851 LappeenrantaFinland
出 版 物：《Frontiers of Electrical and Electronic Engineering in China》 (中国电气与电子工程前沿（英文版）)
年 卷 期：2011年第6卷第2期
页 面：328-338页
学科分类：082903[工学-林产化学加工工程] 08[工学] 0829[工学-林业工程] 082201[工学-制浆造纸工程] 0822[工学-轻工技术与工程]
基 金：The work was partially supported by the following projects:PapVision(http://www.it.lut.fi/project/papvision/)financed by the European Union(Tekes project No.70049/03 and 70056/04) the Academy of Finland(Project 204708)
主 题：adaptive thresholding paper quality inspection picking machine vision
摘 要：Fine and sparse details appear in many quality inspection applications requiring machine *** on flat surfaces,such as paper or board,the details can be made detectable by oblique *** this study,a general definition of such details is given by defining sufficient statistical properties from *** statistical model allows simulation of data and comparison of methods designed for detail *** on the definition,utilization of the existing thresholding methods is shown to be well *** comparison shows that minimum error thresholding outperforms the other standard ***,the results are successfully applied to a paper printability inspection application,and the IGT picking assessment,in which small surface defects must be *** provided method and measurement system prototype provide automated assessment with results comparable to manual expert evaluations in this laborious task.
维普期刊数据库