Systemization of Visual Inspecting Processes for Groung Surfaces Using Image Processing Method
| Project/Area Number |
12650108
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
機械工作・生産工学
|
|---|
| Research Institution | CHIBA UNIVERSITY |
|---|
Principal Investigator |
HIGUCHI Shizuichi CHIBA UNIV., ENGRG., ASSOCIATE PROF., 工学部, 助教授 (50114319)
|
|---|
| Project Period (FY) |
2000 – 2001
|
| Project Status |
Completed (Fiscal Year 2001)
|
| Budget Amount *help |
¥2,600,000 (Direct Cost: ¥2,600,000)
Fiscal Year 2001: ¥700,000 (Direct Cost: ¥700,000)
Fiscal Year 2000: ¥1,900,000 (Direct Cost: ¥1,900,000)
|
|---|
| Keywords | Systemization / Visual inspecting process / Image processing / Hairline finishing / Gray level co-occurrence matrix / ヘアライン / 特徴量 / 傷 |
|---|
| Research Abstract |
It is useful to systemize visual inspecting processes carried by skilled workers for ground surfaces. For this purpose, the hairline finished surfaces were inspected using the extracted features of them. Hairline finishing, which leaves a detailed continuous line pattern on the surface of a metal, is being used widely in industrial products for its ornamental and functional effects. However, the synthetic evaluation of them is done in many cases sensuously and subjectively though visual inspection by skilled workers because evaluation is based on geometrical continuity and regularity of the line pattern. The aim of this research is to develop a method to evaluate hairline finished surfaces objectively and quantitatively by image processing.
First the pictures of them were taken using a CCD camera in the size of 3 mm X 3 mm, and processed to remove influence of the color unevenness and the difference in the brightness. Next, the textural analysis processing was carried out by estimating the gray level co-occurrence matrix which indicates the rate of combination of two gray level pixels in picture. This textural analysis is effective because there was a clear difference in the textural features between the pictures judged as good and the pictures judged as bad.
In consideration of these results, an evaluation system was developed using a combination of textural feature values.
|
Report
(3 results)
Research Products
(7 results)
