EP0501784A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Method and apparatus for optically determining the acceptability of products
Assignee: Philip Morris Products Inc
•
Filing: 1992-02-26
•
Granted: —
•
Expires: 2012-02-26
Abstract
Abstract The acceptability of the appearance of objects (12) such as consumer products is determined by forming an initial discriminant function (F) as a composite of a relatively small number of images (I) which are known to be acceptable. This initial discriminant function is then used to gather statistical information (P, A, B, C) about how a first relatively large number of images compare to the initial discriminant function. Thereafter, this statistical information is used (318-324) to select or aid in the selection of acceptable images from a second relatively large number of images, and the images selected as acceptable are used (334) to refine the discriminant function. The refined discriminant function is then used (e.g., during actual product inspection (402-414)) to determine which objects have an acceptable appearance and which do not. <IMAGE>
Inventors
- 👤 Kenneth A. Cox
- 👤 Henry M. Dante
- 👤 Robert J. Maher
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-30 04:46
CPC Classifications
G; G01; G01N; G01N21/00; G01N21/84; G01N21/88; G01N21/8851; B; B07; B07C; B07C5/00; B07C5/04; B07C5/10; G06; G06F; G06F18/00; G06F18/20; G06F18/21; G06T; G06T7/00; G06T7/0002; G06T7/0004; G06T7/001; G06V; G06V10/00; G06V10/70; G07; G07C; G07C3/00; G07C3/14; G06T2207/00; G06T2207/30; G06T2207/30108; G06T2207/30164
Claims Analysis
Total Claims: 20
Claim 1
Independent Claim
232 words
A method of determining the acceptability of a product (12) by generating a filter (F) from a first set of acceptable images (I) of the product, comparing the filter with each of a second set of images of the product to produce a processed value (P) for each image in the second set, the processed values having a distribution of values, comparing the filter with each of a third set of images of the product to produce a further processed value for each image in the third set, and comparing each further processed value to the distribution to determine the acceptability of the product associated with the image having the further processed value, characterized by: generating (220) from the distribution a first range (A) and a second range (B) of processed values, the first range comprising processed values associated with acceptable images of the product, and the second range being spaced from said first range and comprising processed values associated with unacceptable images of the product; determining (318, 322, 324) whether each further processed value is outside both of the first and second ranges and, if so, selecting the associated image only if said image is acceptable; and adaptively training (334) the filter with the selected image to produce a modified filter whereby comparison of the modified filter with the selected image produces a modified processed value closer to the first range.
Claim 2
Dependent Claim
35 words
A method according to Claim 1, characterized in generating the filter from the first set of acceptable images of the product comprises combining (120) the first set of acceptable images using a logical OR operation.
Claim 3
Dependent Claim
80 words
A method as claimed in Claim 2, further characterized in that the step of combining the first set of acceptable images includes the steps of: edge detecting (108) each image; and associating (108) a first value with each portion of each edge detected image which has a value on one side of a predetermined threshold value, and associating a second value with all other portions of each edge detected image prior to combining the images using the logical OR operation.
Claim 4
Dependent Claim
19 words
A method according to Claim 3, characterised in that the first and second values are binary 0 and 1.
Claim 5
Independent Claim
26 words
A method according to any of Claims 1 to 4, characterized in that the adaptive training of the filter is analogous to a Widrow-Hoff training algorithm.
Claim 6
Independent Claim
31 words
A method according to any of Claims 1 to 5, characterized in that the selected image is selected manually (324) based on the appearance of the product associated with the image.
Claim 7
Independent Claim
30 words
A method according to any of Claims 1 to 6, characterised by adaptively training the filter with the associated image if the further processed value is in the first range.
Claim 8
Independent Claim
33 words
A method according to any preceding claim, wherein the processed values of each image in the second set are the dot product of the filter and each of the second set of images.
Claim 9
Independent Claim
37 words
A method according to any preceding claim, characterised by sub-dividing each of the acceptable images into a plurality of image portions and performing all of the foregoing steps upon at least some of the image portions individually.
Claim 10
Dependent Claim
241 words
Apparatus for determining the acceptability of a product (12) by generating a filter (F) from a first set of acceptable images (I) of the product, comparing the filter with each of a second set of images of the product to produce a processed value (P) for each image in the second set, the processed values having a distribution of values, comparing the filter with each of a third set of images of the product to produce a further processed value for each image in the third set, and comparing each further processed value to the distribution to determine the acceptability of the product associated with the image having the further processed value, characterized by: means (26, 220) for generating from the distribution a first range (A) and a second range (B) of processed values, the first range comprising processed values associated with acceptable images of the product, and the second range being spaced from the first range and comprising processed values associated with unacceptable images of the product; means (26, 318, 322, 324) for determining whether each further processed value is outside both of the first and second ranges and, if so, selecting the associated image only if said image is acceptable; and means (26, 334) for adaptively training the filter with the selected image to produce a modified filter whereby the comparison of the modified filter with the selected image produces a modified processed value closer to the first range.
Claim 11
Dependent Claim
39 words
Apparatus according to Claim 10, characterized in that the filter is generated from the first set of acceptable images of the product by means (26, 120) for combining the first set of acceptable images using a logical OR operation.
Claim 12
Dependent Claim
80 words
Apparatus according to Claim 11, characterised in that the means for combining the first set of acceptable images comprises: means (26, 108) for edge detecting each image; and means (26, 108) for associating a first value with each portion of each edge detected image which has a value on one side of a predetermined threshold value, and associated a second value with all other portions of each edge detected image prior to combining the images using the logical OR operation.
Claim 13
Dependent Claim
18 words
Apparatus according to Claim 12, characterized in that the first and second values are binary 1 and 0.
Claim 14
Independent Claim
30 words
The apparatus as claimed in any of Claims 10 to 13, characterized in that the means (26, 334) for adaptively training performs a function analogous to a Widrow-Hoff training algorithm.
Claim 15
Dependent Claim
35 words
Apparatus according to any of Claims 10 to 14, characterized in that the means for determining includes means (26, 324) for allowing manual selection based on the appearance of the product associated with the image.
Claim 16
Dependent Claim
33 words
Apparatus according to any of Claims 10 to 15, characterized by means (26) for adaptively training the filter with an image associated with a further processed value which is in the first range.
Claim 17
Dependent Claim
41 words
Apparatus according to any of Claims 10 to 16, characterized by means for forming the dot product of the filter and each of the second set of images to form the processed values of each image in the said second set.
Claim 18
Dependent Claim
45 words
Apparatus according to any of Claims 10 to 17, characterized by a video camera (24) for forming at least one of the first, second and third sets of images, and by means for positioning a product in the field of view of the video camera.
Claim 19
Dependent Claim
21 words
Apparatus according to Claim 18, characterized by means for illuminating the product in the field of view of the video camera.
Claim 20
Dependent Claim
32 words
Apparatus according to Claim 19 or 20, characterized in that the positioning means comprises a conveyor (20) for conveying products are after another through the field of view of the video camera.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.