Printed Circuit Board Inspection - A Novel Approach

Lees, David E. B.; Henshaw, Philip D.

doi:10.1117/12.937872

Cited by 7 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar goal-driven attentive process is seeking out an object with certain features that varies from what is expected. This is the case in industrial tasks that require detection of a part that is out of tolerance, e.g., 'dimensionality checking' on the foils of printed circuit boards [14]. If a particular foil is too narrow or too wide, it can attract attention as a dimensionality violation.…”

Section: Focusing-of-attention In Attentive Sensingmentioning

confidence: 99%

“…When complete a priori knowledge is available about a feature in an image and this feature varies from known tolerances, attention should be focused on the region with the non-conforming feature. This type of attentive focusing is commonly carried out in industrial inspection, such as in printed circuit board inspection [14]. When a particular feature tolerance (such as a minimum foil width) is violated, attention is focused on the region.…”

Section: Expectancy Variation Foa Mechanism: This Second Top-down Foamentioning

confidence: 99%

See 1 more Smart Citation

<title>Attentive sensing strategy for a multiwindow vision architecture</title>

Barth

Hackwood

Beni

1990

Parallel Architectures for Image Processing

View full text Add to dashboard Cite

A multi-window video architecture is a unique coarse-grained multiprocessor implementation used for image processing. Such an architecture consists of many local rectangular regions (windows) that are processed in parallel by individual processing units. The architecture provides many windows, whose position, size, shape and sampling rate are individually controllable. Each window captures image data into its own local memory, so image memory contention is eliminated. The motivation behind multi-windowing stems from the fact that there is often an excess of information in an image; we usually are only interested in a few objects that require further processing. By performing the processing in parallel only within windows, processing speeds are greatly increased.A key problem in multi-windowing is how to automatically assign windows to the relevant objects within an image. In order to address this problem, we introduce a strategy that models itself closely to the human attention ability, therefore we refer to it as an attentive sensing strategy. The attentive sensing strategy is carried out in two stages. The first 'pre-attent.ive' stage consists of several parallel processing units which rapidly extract salient information in parallel across the entire image. The second stage, termed 'attentive sensing', consists of a distribution of focused sensory processing on only the salient objects in the image. Information gathered by the pre-attentive stage guides the processing of the attentive stage, resulting in the elimination of irrelevant information. We carry out this sensing strategy on a multi-windowing vision system designed and built for the inspection of integrated circuit wafers.

show abstract

Section: Focusing-of-attention In Attentive Sensingmentioning

confidence: 99%

Section: Expectancy Variation Foa Mechanism: This Second Top-down Foamentioning

confidence: 99%

<title>Attentive sensing strategy for a multiwindow vision architecture</title>

Barth

Hackwood

Beni

1990

Parallel Architectures for Image Processing

View full text Add to dashboard Cite

show abstract

“…Reference comparison method needs to store a template image in advance, and compare test images with the template image in pixel‐to‐pixel or feature‐to‐feature level. If any pixels or features do not match, then defects may exist [1–3]. Therefore, the idea of reference comparison method is rather straightforward thus easy to be implemented.…”

Section: Introductionmentioning

confidence: 99%

Recurrent spatial transformer network for high‐accuracy image registration in moving PCB defect detection

Huang

Hua

et al. 2020

J. eng.

View full text Add to dashboard Cite

“…The function of these systems is as follows: the faulty samples should be selected and repaired or removed before each critical technological step of production. The main AOI techniques [1][2][3][4][5] are as follows: (i) reference-based methods [6] (a comparison with a reference or to a good sample), (ii) non-referential methods (rule-based method) [7] and (iii) hybrid methods [4] are combination of the two previous methods. Some hybrid methods based on CNN paradigm [8,9] will be shown in this contribution.…”

Section: Introductionmentioning

confidence: 99%

Some new analogic CNN algorithms for PCB quality control

Hidvégi

Szolgay

2002

Circuit Theory & Apps

View full text Add to dashboard Cite

SUMMARYIn the production of a PCB di erent errors may occur. The detection of these errors is time consuming and there is an increasing need to use a 100% quality control in production. New analogic CNN algorithms were developed to detect the short circuit and the misalignment errors. These analogic algorithms were tested with software simulator, 20 × 22 CNN-UM chip and 64 × 64 CNN-UM chip by using ALADDIN System.

show abstract

Printed Circuit Board Inspection - A Novel Approach

Cited by 7 publications

References 0 publications

<title>Attentive sensing strategy for a multiwindow vision architecture</title>

<title>Attentive sensing strategy for a multiwindow vision architecture</title>

Recurrent spatial transformer network for high‐accuracy image registration in moving PCB defect detection

Some new analogic CNN algorithms for PCB quality control

Contact Info

Product

Resources

About