Patent US5321767A successfully refreshed from Google Patents.
US5321767A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method of forming a mask in image processing operation
Assignee: Cognex Technology and Investment LLC
•
Filing: 1992-08-28
•
Granted: 1994-06-14
•
Expires: 2012-08-28
Abstract
Abstract A process for examining the appearance of an examination object has the steps of taking an image of the object to obtain image data and processing the image data by an image processing apparatus. A mask is formed to determine, in the image data to be processed, a non-examination region of various configurations and, when the position of the examination object is deviated from the correct position, the position of the mask also is shifted correspondingly to enable appearance examination in varying conditions. To this end, a brightness threshold value is set in the input multi-value image data so as to define the non-examination region to be excluded from said examination region, thereby forming said mask, and the pixels having gradation levels not higher or lower than the threshold value are excluded from the examination region.
Inventors
- 👤 Takahiro Murase
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-08 06:32
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0004; G06T7/001; G06T7/70
Claims Analysis
Total Claims: 14
Claim 1
Independent Claim
328 words
A process for examining the appearance of a plurality of examination objects to detect any defect in said examination objects, said process comprising: taking an image of each said examination object to obtain input multi-value image data showing the appearance of each said examination object, each said image including an examination region which is determined by a known function, forming for each said examination region a mask indicating a nonexamination region which is to be excluded from the processing of said input multi-value image data for a respective examination object, wherein the mask is formed by setting a brightness threshold value in the input multi-value image data so as to define a non-examination region to be excluded from an examination region; and processing the input multi-value image data by an image processing apparatus, wherein the examination position of an examination object at the time of examination can vary from the correct position for examination, said process further comprising the steps of: storing, as reference image data, the input multi-value image data of a preselected portion of one of said examination objects when located at the correct position; computing the positional relationship between said reference image data and at least one of an examination region on an examination object and said mask; inputting the image data of another of said examination objects when located at an examination position; computing, by a pattern matching technique, the position of the portion of the inputted image data of said another examination object which corresponds to said preselected portion; and positioning said examination region and said mask for said another examination object with respect to said portion of the inputted image data for said another examination object on the basis of said positional relationship; and then processing only the input multi-value image data for the portion of the examination region for said another examination object which excludes the non-examination region, to thereby detect any defects in the appearance of said another examination object.
Claim 2
Dependent Claim
328 words
A process for examining the appearance of a plurality of examination objects to detect any defect in said examination objects, said process comprising: taking an image of each said examination object to obtain input multi-value image data showing the appearance of each said examination object, each said image including an examination region which is determined by a known function, forming for each said examination region a mask indicating a nonexamination region which is to be excluded from the processing of said input multi-value image data for a respective examination object, wherein the mask is formed by setting a brightness threshold value in the input multi-value image data so as to define a non-examination region to be excluded from an examination region; and processing the input multi-value image data by an image processing apparatus, wherein the examination position of an examination object at the time of examination can vary from the correct position for examination, said process further comprising the steps of: storing, as reference image data, the input multi-value image data of a preselected portion of one of said examination objects when located at the correct position; computing the positional relationship between said reference image data and at least one of an examination region on an examination object and said mask; inputting the image data of another of said examination objects when located at an examination position; computing, by a pattern matching technique, the position of the portion of the inputted image data of said another examination object which corresponds to said preselected portion; and positioning said examination region and said mask for said another examination object with respect to said portion of the inputted image data for said another examination object on the basis of said positional relationship; and then processing only the input multi-value image data for the portion of the examination region for said another examination object which excludes the non-examination region, to thereby detect any defects in the appearance of said another examination object.
Claim 3
Dependent Claim
232 words
A process for examining the appearance of examination objects to detect any defect in the examination objects, wherein the examination position of an examination object at the time of examination can vary from the correct position for examination, said process comprising the steps of: storing, as reference image data, the image data of a preselected portion of one of said examination objects when said one of said examination objects is located at the correct position for examination; computing the positional relationship between said reference image data and at least one of an examination region of an examination object and a mask for masking a portion of said examination region, said examination region being defined by a known factor; inputting the image data of another of said examination objects when located at its examination position; computing, by a pattern matching technique, the position of the portion of the inputted image data of said another examination object which corresponds to said preselected portion; positioning said examination region and said mask with respect to said portion of the inputted image data for said another examination object on the basis of said positional relationship; and then processing only that portion of the inputted image data for said another examination object which corresponds to said examination region excluding the portion thereof masked by said mask, to detect any defects in the appearance of said another examination object.
Claim 4
Dependent Claim
232 words
A process for examining the appearance of examination objects to detect any defect in the examination objects, wherein the examination position of an examination object at the time of examination can vary from the correct position for examination, said process comprising the steps of: storing, as reference image data, the image data of a preselected portion of one of said examination objects when said one of said examination objects is located at the correct position for examination; computing the positional relationship between said reference image data and at least one of an examination region of an examination object and a mask for masking a portion of said examination region, said examination region being defined by a known factor; inputting the image data of another of said examination objects when located at its examination position; computing, by a pattern matching technique, the position of the portion of the inputted image data of said another examination object which corresponds to said preselected portion; positioning said examination region and said mask with respect to said portion of the inputted image data for said another examination object on the basis of said positional relationship; and then processing only that portion of the inputted image data for said another examination object which corresponds to said examination region excluding the portion thereof masked by said mask, to detect any defects in the appearance of said another examination object.
Claim 5
Dependent Claim
56 words
A process according to claim 2, wherein said inputted image data for said another examination object is given in the form of multigradation pixel signals carried by a multiplicity of pixels, and the pixels having brightness not lower than a threshold level are masked by said mask so as to be excluded from the examination region.
Claim 6
Dependent Claim
28 words
A process according to claim 3, further comprising contracting said mask by shifting the edge of said mask inwardly of said mask by a predetermined number of pixels.
Claim 7
Dependent Claim
28 words
A process according to claim 3, further comprising expanding said mask by shifting the edge of said mask outwardly of said mask by a predetermined number of pixels.
Claim 8
Dependent Claim
56 words
A process according to claim 2, wherein said inputted image data for said another examination object is given in the form of multigradation pixel signals carried by a multiplicity of pixels, and the pixels having brightness not higher than a threshold level are masked by said mask so as to be excluded from the examination region.
Claim 9
Dependent Claim
28 words
A process according to claim 6, further comprising contracting said mask by shifting the edge of said mask inwardly of said mask by a predetermined number of pixels.
Claim 10
Dependent Claim
28 words
A process according to claim 7, further comprising expanding said mask by shifting the edge of said mask outwardly of said mask by a predetermined number of pixels.
Claim 11
Dependent Claim
39 words
A process according to claim 2, wherein each examination object comprises an article having at least one printed symbol on a surface thereof, and said mask excludes the inputted image data corresponding to said at least one printed symbol.
Claim 12
Dependent Claim
37 words
A process in accordance with claim 2 wherein each examination object comprises an article having a complicated configuration, and said mask excludes the inputted image data corresponding to at least an edge portion of the respective article.
Claim 13
Dependent Claim
214 words
In a process for examining the appearance of an examination object to detect any defect in said examination object by taking an image of said examination object to obtain input multi-value image data showing the appearance of said examination object, said image including an examination region which is determined by a known function, and processing said input multi-value image data by an image processing apparatus, the improvement of forming in said examination region a mask indicating a nonexamination region which is to be excluded from the processing of said input multi-value image data, wherein the mask is formed by setting a brightness threshold value in the input multi-value image data so as to define the non-examination region to be excluded from said examination region; and then processing only the input multi-value image data for the portion of said examination region which excludes said non-examination region, to thereby detect any defects in the appearance of said examination object; wherein said examination object comprises an article having at least one printed symbol on a surface thereof, and said brightness threshold value excludes the input multi-value image data corresponding to said at least one printed symbol, whereby the appearance of a portion of said examination object other than said at least one printed symbol can be examined.
Claim 14
Dependent Claim
214 words
In a process for examining the appearance of an examination object to detect any defect in said examination object by taking an image of said examination object to obtain input multi-value image data showing the appearance of said examination object, said image including an examination region which is determined by a known function, and processing said input multi-value image data by an image processing apparatus, the improvement of forming in said examination region a mask indicating a nonexamination region which is to be excluded from the processing of said input multi-value image data, wherein the mask is formed by setting a brightness threshold value in the input multi-value image data so as to define the non-examination region to be excluded from said examination region; and then processing only the input multi-value image data for the portion of said examination region which excludes said non-examination region, to thereby detect any defects in the appearance of said examination object; wherein said examination object comprises an article having at least one printed symbol on a surface thereof, and said brightness threshold value excludes the input multi-value image data corresponding to said at least one printed symbol, whereby the appearance of a portion of said examination object other than said at least one printed symbol can be examined.
References Cited (Backward Citations)
US4583125A
Cited
US5060280A
Cited
US5140650A
Cited
US5034986A
Cited
US5115475A
Cited
JPH04165577A
Cited
US5218645A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-06-13 | 1997-12-13 | 1998-06-14 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-06-13 | 2001-12-13 | 2002-06-14 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-06-13 | 2005-12-13 | 2006-06-14 | $7700.00 | Window Closed / Lapsed |