Abstract
This paper presents a new method for modelling and locating objects in
images for applications such as Printed Circuit Board (PCB) inspection.
Objects of interest are assumed to exhibit little variation in size or shape
from one example to the next, but may vary considerably in grey-level appearance.
Simple correlation based approaches perform poorly on such
examples. We demonstrate how a statistical model based approach combined
with a multi-resolution search can accurately locate objects and reliably
distinguish between good and bad components. We describe a 'bootstrap'
approach to training and a method of automatically refining the final
model to improve its performance. We demonstrate the method on PCB
inspection, showing the approach is robust enough for use in a real production
environment.
images for applications such as Printed Circuit Board (PCB) inspection.
Objects of interest are assumed to exhibit little variation in size or shape
from one example to the next, but may vary considerably in grey-level appearance.
Simple correlation based approaches perform poorly on such
examples. We demonstrate how a statistical model based approach combined
with a multi-resolution search can accurately locate objects and reliably
distinguish between good and bad components. We describe a 'bootstrap'
approach to training and a method of automatically refining the final
model to improve its performance. We demonstrate the method on PCB
inspection, showing the approach is robust enough for use in a real production
environment.
| Original language | English |
|---|---|
| Title of host publication | British Machine Vision Conference |
| Place of Publication | Birmingham |
| Publisher | BMVA Press |
| Pages | 533-542 |
| Number of pages | 10 |
| Volume | 6 |
| DOIs | |
| Publication status | Published - 1995 |
| Event | British Machine Vision Conference - Duration: 1 Jan 1824 → … |
Conference
| Conference | British Machine Vision Conference |
|---|---|
| Period | 1/01/24 → … |