Image analysis – Image transformation or preprocessing – General purpose image processor
Reexamination Certificate
1998-01-28
2001-08-28
Couso, Yon J. (Department: 2723)
Image analysis
Image transformation or preprocessing
General purpose image processor
C382S205000
Reexamination Certificate
active
06282328
ABSTRACT:
RESERVATION OF COPYRIGHT
The disclosure of this patent document contains material that is subject to copyright protection. The owner thereof has no objection to facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the U.S. Patent and Trademark Office patent file or records, but otherwise reserves all copyright rights whatsoever.
BACKGROUND OF THE INVENTION
The invention pertains to machine vision and, more particularly, to the morphological transformation of images, e.g., via dilation and erosion, suitable for use with non-uniform offsets.
Machine vision is the automated analysis of images to determine characteristics of objects shown in them. It is often employed in automated manufacturing lines, where images of components are analyzed to determine placement and alignment during assembly. Machine vision is also used for quality assurance. For example, in the semiconductor device industry, images of chips are analyzed to insure that leads, solder paste and other components do not overrun designated boundaries.
In many machine vision applications, so-called dilation and erosion software “tools” are used to emphasize or de-emphasize patterns in digital images and, thereby, to facilitate the recognition of objects in them. They are generally applied during image preprocessing, that is, prior to pattern recognition. As a result, they are referred to as morphological (or shape-based) transformation tools.
As its name implies, the dilation tool is used to enlarge features in an image. Roughly speaking, it does this by replacing each pixel (or point) in the image with its brightest neighbor. For example, if a given pixel has an intensity of 50 and one of its nearby neighbors has an intensity of 60, the value of the latter is substituted for the former. Application of this tool typically enlarges and emphasizes foreground surfaces, edges and other bright features.
The erosion tool does just the opposite. It de-emphasizes bright features by eroding their borders. Rather than replacing each pixel with its brightest neighbor, this tool replaces each with its dimmest, or least intense, neighbor. This can have the effect of diminishing bright foreground features, though, it is typically used to eliminate small imaging artifacts, such as those resulting from reflections, scratches or dust.
Prior art dilation and erosion tools are legion. A problem with many such tools, however, is that they cannot be readily adapted to compensate for a wide range of image-capture environments. One particular problem in this regard is uneven illumination, which can alter an image so much so as to make pattern recognition difficult.
Although fast, accurate and flexible morphological vision tools are marketed by Cognex Corporation, the assignee hereof, there remains a need for still better such tools. Accordingly, an object of this invention is to provide machine vision systems and methods for morphological transformation of images, e.g., acquired with poor illumination.
A more particular object of the invention is to provide such systems and methods as can be used to generate image dilations and erosions, e.g., with non-uniform offsets.
A further object of the invention is to provide such systems as operate accurately and rapidly, yet, without requiring unduly expensive processing equipment or without undue consumption of resources.
A related object of the invention is to provide such systems as can be implemented on conventional digital data processors or other conventional machine vision analysis equipment, without excessive cost or difficulty.
SUMMARY OF THE INVENTION
The foregoing are among the objects attained by the invention, which provides machine vision systems and methods for morphological transformation of a source image, e.g., with non-uniform offsets. Such methods have application, for example, in inspection applications where illumination is not uniform.
In one aspect, the invention provides a method of morphological transformation of an image in which the pixels from selected “neighborhoods,” or regions, of the source image are rearranged, or unfolded, into respective columns of an intermediate image. Thus, for example, the first 3×3 neighborhood in the source image can be unfolded into one column of the intermediate image; the second 3×3 neighborhood into the second column; and so forth. The unfolded neighborhoods can be stored in a data store, such as a cache memory or buffer, of a digital data processing system on which the invention is practiced.
For each column in the intermediate image, the method identifies a pixel intensity value of selected rank. Where the method is employed to effect a dilation transformation, for example, the method identifies the maximum pixel intensity in each column. For an erosion transformation, the method seeks the minimum value in each column. Other transformations may require averages or other functions of the compared pixel intensities. The pixel intensity value of selected rank (e.g., minimum or maximum) can be determined, e.g., by a series of pair-by-pair comparisons among the values in each column, by sorting the column, or by an en masse operation, e.g., using a register-level instruction of a superscalar processor.
Once the pixel intensity value of selected rank is identified for each column, it is retained in a transformation image, e.g., at a location corresponding to center of the respective neighborhood. Thus, for example, in a dilation operation, the maximum pixel intensity value for the first column can be stored in the transformation image at a location corresponding to the center of the first neighborhood; that for the second column, the center of the second neighborhood; and so forth.
Take, for example, a 6×3 region of a source image whose pixel intensities are as follows:
11
2
3
4
15
7
6
12
8
14
10
16
1
7
13
9
5
3
&AutoRightMatch;
The first two non-overlapping neighborhoods in that image can be unfolded as follows:
11
4
2
15
3
7
6
14
12
10
8
16
1
9
7
5
13
3
&AutoRightMatch;
The maximum pixel intensisty values, for purposes of a dilation operation, are as follows:
13
16
These values also constitute the maximum pixel intensity values for the corresponding neighborhoods constituting the pixels
11
,
2
,
3
,
6
,
12
,
8
,
1
,
7
,
13
and
4
,
15
,
7
,
14
,
10
,
16
,
9
,
5
,
3
, respectively. Accordingly, they can be stored in the transformation image at locations corresponding to the centers of those respective neighborhoods, i.e., at locations corresponding to the original pixels of intensity 12 and 10, respectively.
The foregoing steps are repeated, e.g., along strips or bands, for each neighborhood in the source image.
Further aspects of the invention provide methods as described above in which an offset is added to each pixel intensity value prior to its comparison with other values in the column. According to this aspect of the invention, selected columns or pixels a first row of the intermediate image are loaded into corresponding columns in a first data store, e.g., a processor register. Selected columns of a second row of that image are likewise loaded into a second data store, e.g., another processor register. Offsets are added to the intensity values in each of the first and second stores. For this purpose, an array of offsets—one corresponding to each column in the data stores—can itself be stored in a processor register. As above, respective columns of the offset-adjusted data stores are compared with one another to identify the pixel intensity value of selected rank.
The “winners” of each respective pair-by-pair comparison are stored in the first data store, so that the process can be repeated for the remaining values in the respective neighborhoods. For example, following storage of the winners for the first and second rows, the pixels in a third row of the intermediate image are loaded into corresponding columns in the second data store. An offset is then added to each of those values, prior to their being compared with corresponding values in the fir
Cognex Corporation
Couso Yon J.
Powsner David J.
LandOfFree
Machine vision systems and methods for morphological... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Machine vision systems and methods for morphological..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Machine vision systems and methods for morphological... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2534467