Project/Area Number |
11650109
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Single-year Grants |
Section | 一般 |
Research Field |
Materials/Mechanics of materials
|
Research Institution | KONAN UNIVERSITY |
Principal Investigator |
NAKAYASU Hidetoshi KONAN UNIVERSITY, PROFESSOR, 理工学部, 教授 (80142553)
|
Co-Investigator(Kenkyū-buntansha) |
NAKAGAWA Masao SHIGA UNIVERSITY, ASSISTANT, 経済学部, 助手 (40283551)
MAEDA Kazuaki KONAN UNIVERSITY, LECTURER, 理工学部, 講師 (90319830)
|
Project Period (FY) |
1999 – 2002
|
Project Status |
Completed (Fiscal Year 2002)
|
Budget Amount *help |
¥2,400,000 (Direct Cost: ¥2,400,000)
Fiscal Year 2002: ¥400,000 (Direct Cost: ¥400,000)
Fiscal Year 2001: ¥400,000 (Direct Cost: ¥400,000)
Fiscal Year 2000: ¥400,000 (Direct Cost: ¥400,000)
Fiscal Year 1999: ¥1,200,000 (Direct Cost: ¥1,200,000)
|
Keywords | Visual inspection / Intelligent image processing / Rule-based decision table / Human oriented design / 感能検査 / 視覚情報処理 / 恒常刺激法 / 外観検査 / 信頼性 / 画像処理 / ニューラルネットワーク / ルールテーブル / FRPパネル / 欠陥分類 / 表面検査画像 / 目視検査 |
Research Abstract |
Recently, several kinds of image processing method has been applying to the automated visual inspection system for defects on the product surface. One of the aims of this research is also in the development of a heuristic and emergence algorithm which is used in the judgement process in the automated visual inspection system instead of expert inspector. A sort capacity by human vision is extremely high-performance, therefore such a soft information processing to retrieve defects from inspection image has been regarded unfit on the computer which is good at digital information processing. On the other hand, a visual inspection process has been holding the problem in productivity, since the performance of a precision and a speed will be degraded by fatigue of the inspector. In order to meet these problems, some research works were tried for the standardization of an operation time of visual inspection, though it is not reached to the place which fixes a good evaluation measure. On the other hand, the development of productivity and performance for computerized inspection system which have a feature of recognition like human being has been left with a lots of problems unsolved. This paper deals with the automated visual inspection method for advanced manufacturing in order to enhance human skill with machine performance for improved management of product flexibility and product quality. The defective picture sampling process based on the proposed algorithm is performed for original picture image for a check of the industrial product. In the proposed algorithm, three kinds of inspection information such as location, size and level of defects are treated for clustering image data.
|