EP0435660A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method of evaluating object based upon image processing, and inspection apparatus using said method
Assignee: Canon Inc
•
Filing: 1990-12-24
•
Granted: —
•
Expires: 2010-12-24
Abstract
Abstract Method and apparatus for automatic inspection of, for example, the soldering of surface-mounted ICs. Images of the object under inspection are evaluated by two processing methods: "reverse-truth-value definition" and "fuzzy clustering". The results of the evaluations are combined to produce a decission for quality-control.
Inventors
- 👤 Eiji Nishimori
- 👤 Toshiaki Shingu
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-04 18:26
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0004; G06T7/0006; G06T5/00; G06T5/70; G06T7/001; G06T2207/00; G06T2207/10; G06T2207/10024; G06T2207/20; G06T2207/20076; G06T2207/30; G06T2207/30108; G06T2207/30141
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
59 words
An evaluation method for acquiring an image of an object of evaluation and evaluating the object based upon the image, comprising the steps of: extracting a plurality of characterizing quantities from input image data; performing a first evaluation by fuzzy clustering based upon the characterizing quantities; and performing a second evaluation by another method based upon the characterizing quantities.
Claim 2
Dependent Claim
16 words
The method according to claim 1, wherein said another method is a reverse truth-value definition method.
Claim 3
Dependent Claim
22 words
The method according to claim 1, further comprising a step of coupling results of evaluation performed by said first and second evaluations.
Claim 4
Dependent Claim
22 words
The method according to claim 2, further comprising a step of coupling results of evaluation performed by said first and second evaluations.
Claim 5
Dependent Claim
67 words
An inspection apparatus for acquiring an image of an object of evaluation and evaluating the object based upon the image, comprising: means for extracting a plurality of characterizing quantities using input image data; and means for inspecting the object, using the plurality of characterizing quantities extracted by said extracting means, based upon plural results of evaluations performed in accordance with a plurality of methods employing different principles.
Claim 6
Dependent Claim
18 words
The apparatus according to claim 5, wherein said object is a mounted state of a printed circuit board.
Claim 7
Dependent Claim
22 words
The apparatus according to claim 5, wherein said characterizing quantities include at least one of position information, shape information and brightness information.
Claim 8
Dependent Claim
26 words
The apparatus according to claim 5, wherein said plurality of methods include at least one of a reverse truth-value definition method and a fuzzy clustering method.
Claim 9
Dependent Claim
26 words
The apparatus according to claim 7, wherein said plurality of methods include at least one of a reverse truth-value definition method and a fuzzy clustering method.
Claim 10
Dependent Claim
47 words
The apparatus according to claim 9, wherein said reverse truth-value definition method uses position information from among said characterizing quantities, said fuzzy clustering method uses said shape information and said brightness information, and said inspection apparatus further comprises means for coupling results obtained by said two methods.
Claim 11
Dependent Claim
47 words
The apparatus according to claim 9, wherein said reverse truth-value definition method uses position information from among said characterizing quantities, said fuzzy clustering method uses said shape information and said brightness information, and said inspection apparatus further comprises means for coupling results obtained by said two methods.
Claim 12
Dependent Claim
88 words
An inspection apparatus for inspecting the surface state of a substrate board comprising: reading means for reading said surface of said substrate board in a form of multivalued image data; binarizing means for binarizing the multivalued image data read by said reading means into binary data; extraction means for extracting characterizing quantities of the surface of said substrate board on the basis of said multivalued image data and said binary data; and evaluating means for evaluating the surface of said substrate board in accordance with said characterizing quantities.
Claim 13
Dependent Claim
14 words
The apparatus according to claim 12, wherein said reading means comprises a CCD sensor.
Claim 14
Dependent Claim
24 words
The apparatus according to claim 12, further comprising noise removal means for removing noises included in multivalued image data read by said reading means.
Claim 15
Dependent Claim
22 words
The apparatus according to claim 12, wherein said characterizing quantities include at least one of position information, shape information and brightness information.
Claim 16
Dependent Claim
40 words
The apparatus according to claim 12, wherein said evaluation means evaluates, using said characterizing quantities, the status of said substrate board on the basis of plural results of evaluations performed in accordance with a plurality of methods employing different principles.
Claim 17
Dependent Claim
26 words
The apparatus according to claim 16, wherein said plurality of methods include at least one of a reverse truth-value definition method and a fuzzy clustering method.
Claim 18
Dependent Claim
29 words
The apparatus according to claim 12, wherein said inspection apparatus inspects the substrate board which is soldered, and said evaluating means evaluates a soldered state of the substrate board.
Claim 19
Dependent Claim
97 words
An image processing method comprising: an input step of inputting an image in a form of multivalued image data; a binarizing step of binarizing the multivalued image data input in said input step to binary data; a first extraction step of extracting a first characterizing quantity from said multivalued image data; a second extraction step of extracting a second characterizing quantity from said binary data; and an evaluating step of evaluating said image input in said input step on the basis of said first and second characterizing quantities extracted in said first and second extraction steps respectively.
Claim 20
Dependent Claim
32 words
The method according to claim 19, wherein said evaluation step includes a step of evaluating said image input in said input step on the basis of a plurality of pattern matching methods.
Claim 21
Dependent Claim
18 words
The method according to claim 20, wherein said plurality of pattern matching methods include a fuzzy clustering method.
Claim 22
Dependent Claim
41 words
The method according to claim 21, wherein said evaluation step includes a step of integrating a result of said fuzzy clustering method and an evaluation result which is obtained according to a pattern matching method other than said fuzzy clustering method.
Claim 23
Dependent Claim
23 words
The method according to claim 22, wherein said pattern matching method other than said fuzzy clustering method is a reverse truth-value definition method.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.