JPS6336383A - Picture processor - Google Patents

Abstract

PURPOSE:To speed up the inspection of an object to be inspected, such as the numbers of particles per one article, etc. by removing or extracting the object which is in contact with a boundary between an object area for a picture processing and the object area for a non-processing, rapidly and without depending on the number of the object. CONSTITUTION:In a binary picture memory 3, for instance, the binary image containing 8 pieces of the objects of value '1' which are taken a picture by a television camera and are binarized by a binarization circuit 2, is stored. The line 32 to value '1' is written in a picture frame 31 by a line writing circuit 4, and the object being in contact with the picture frame 31 is connected to one area. The binary image in which the line 32 is written is labeled (numbered) by a labeling circuit 5, at every area of each object in order, and they are stored in a variable density picture memory 6 being labeled by numbers 1-6. If, for instance, a binarization process which extracts the variable density picture of the label number 2 or more, is executed by a binarization circuit 7, the extracted binary image of the object which is not in contact with the picture frame 31, is obtained, which the object in contact with the picture frame 31 is removed.

Description

[Detailed Description of the Invention] [Industrial Application Field] This invention relates to an image processing device that creates and recognizes a binary image of a symmetrical object to be inspected, and in particular, the present invention relates to an image processing device that creates and recognizes a binary image of a symmetrical object to be inspected. The present invention relates to an image processing device suitable for quickly removing or extracting objects that are present in the image.

[Conventional technology]

In a conventional image processing device, in order to identify a symmetrical object, the video signal from the television camera is first converted into digital values of “0” and “1” at a certain threshold level, and then converted to an integer nXm.
In many cases, the amount of information is compressed and processed by storing it in the image memory of the pixel, and various types of identification are performed by determining the feature values of the object, such as area and perimeter, from such binary images. ing. In this way, for example, when inspecting or analyzing cells or particles using image processing, it is often necessary to photograph a large number of objects within the field of view of a television camera, calculate the area of each object, and investigate its distribution. However, at this time, there are cases where only a part of the object is photographed and only part of the object is stored in the image memory, so if you calculate the area distribution etc. including these objects, it will not be stored correctly in the image memory. This results in unreliable data that is different from the distribution of the area of objects stored in the storage area, and processing objects that are only partially stored results in a loss of time.

6(a), 6(b), and 6(c) are explanatory diagrams of the process of determining the distribution of the area of an object in the processing target area in a conventional image processing apparatus of this type. value image,
FIG. 6(b) shows the label processed image, and FIG. 6(c) shows the area for each label.

In FIGS. 6(a) to (c), labels (numbers) 1 to 8 are attached to each object region as shown in FIG. 6(b) for the binary image to be processed in FIG. 6(a). (Labeling process) When calculating the area for each label 1 to 8 as shown in Figure 6 (Q), for labels 1, 4, and 7, only a part of the object is stored in the image memory because it is in contact with the screen frame. Since correct data cannot be obtained due to the lack of information, it is necessary to identify these objects and remove or extract them.

FIG. 7 is an explanatory diagram of the procedure for determining whether or not the object in FIG. 6 is in contact with the boundary of the processing target area.

In FIG. 7, in order to find the coordinate position of each label in the label processed image of FIG. 6(b), each label 1 to 8 is extracted and the The minimum coordinates Xm1n and maximum coordinates Xmax and Y
Find the minimum coordinate w y min and maximum coordinate Ymax of the axis. Figure 8 shows the coordinate values Xm1 of each label 1 to 8 in Figure 7.
FIG. 3 is an explanatory diagram of the results of calculating n, Xmax, Ymin, and Ymax. In Fig. 8, the coordinate values are shown when the size of the image memory in Fig. 6 is 200 horizontally x 200 vertically. The information that it is in contact with the boundary of the target area, that is, the screen frame in this case, is the coordinate value Xa+j
n=0 or Xmax=200, Ymin=O or Ym
Either ax=200. Therefore, it is possible to exclude objects labeled 1.4.7 marked with a star in the figure that meet this coordinate value judgment condition from the processing target as being in contact with the screen frame that is the boundary of the processing target area. can.

However, in the process of determining whether an object is in contact with the boundary of the processing target area in such conventional image processing devices,
Since it is necessary to calculate all the coordinate values of the area for each label and then compare them with the above-mentioned judgment conditions, it takes a considerable amount of time, and the influence increases as the number of objects increases.

[The problem that the invention is trying to solve]

In the conventional technology described above, the coordinate values of each target object are determined to determine whether or not it is in contact with the boundary of the processing target area.
There were problems such as it took a long time to remove or extract objects that were in contact with the screen frame (screen frame), and it was not possible to remove or extract objects that were in contact with the boundary of an arbitrarily shaped processing area. .

An object of the present invention is to provide an image processing method for removing or extracting objects that are in contact with the boundary between a processing target area and a non-processing target area of an object to be inspected at high speed and independent of the number of objects. be.

[Means for solving problems]

The above purpose is to write line data to the boundary between the processing target area and the non-processing target area of the binary image memory of a plurality of objects to be inspected using a line data writing means, After performing processing to connect one or more objects in the binary image to one region, each object in the binary image is labeled by a labeling means and attached to one region connected by the above line data. This is achieved by an image processing device that distinguishes and removes or extracts labels.

[Effect]

In the image processing device, if the area of each object in the binary image memory, which is the image to be processed, has a value of II By writing line data with a value of "11" using the writing means, the area including all the objects touching the boundary can be made into one area, so this binary image must be labeled using the labeling means. In this case, it becomes possible to easily and quickly distinguish objects that are in contact with the boundary from objects that are not in contact with the boundary.

〔Example〕

Embodiments of the present invention will be described below with reference to FIGS. 1 to 5.

FIG. 1 is a block diagram showing an embodiment of an image processing apparatus according to the present invention. In FIG. 1, 1 is a television camera, 2 is a binarization circuit, 3 is a binary image memory, 4 is a line writing circuit, 5 is a labeling circuit, 6 is a grayscale image memory, and 7
8 is a binarization circuit, 8 is a density histogram extraction circuit, 9 is an image processing circuit, 10 is a recognition circuit, and 11 is a processing area designation circuit.

Note that the part surrounded by a dashed-dotted line indicates the main body part of the device.

With the configuration shown in FIG. 1, a video signal captured from a television camera 1 is binarized by a binarization circuit 2 and stored in a binary image memory 3. With respect to the binary image on the binary image memory 3, the line writing circuit 4 writes a line to the boundary of the processing target area specified by the processing area specifying circuit 11. If the target object area has a value of "1'", the same rr 1 +1 Write a line of values. In addition, these two
Labeling circuit 5 for the binary image on the value image memory 3
A label (number) is attached to each object area and stored in the grayscale image memory 6. Based on the labeled grayscale image on the grayscale image memory 6, the processing area specifying circuit 11 determines which objects are in contact with the boundary of the non-processing target area and which objects are not in contact with the boundary of the non-processing target area. Although touching objects can be removed or extracted, if you want to extract objects that are not in contact with the boundary of the processing target area as a binary image, you can use the binarization circuit 7 (same as the binarization circuit 2) to remove or extract objects that are in contact with the boundary. What is necessary is to perform binarization processing to extract the labels of objects that are not labeled. In addition, when calculating the area (pixel number) of each object that is not in contact with the boundary, the density histogram extraction circuit 8 calculates the number of pixels for each label for the labeled grayscale image in the grayscale image memory 6, and then Of the results, it is sufficient to use only the result of the number of pixels of labels that are not in contact with the boundary. Alternatively, in a similar manner, the surface image processing function of another image processing circuit 9 can be used to obtain various feature amounts. Here, the recognition circuit 10 performs processing in various combinations of the binarization circuit 7, the density histogram extraction circuit 8, the image processing circuit 9, etc. according to a pre-prepared image processing means to recognize the object to be inspected. Note that the processing area specifying circuit 11 specifies the processing area where recognition, analysis, etc. are actually performed.

Figures 2 (a), (b), (c), and (d) show an example of the processing procedure for determining whether or not the object in Figure 1 is in contact with the boundary (screen frame) of the processing target area. This is an explanatory diagram shown in Figure 2 (a
) is a binary image memory 3 with a boundary (screen frame) 31 of the processing area, FIG. 2(b) is a binary image memory 3 with a line 32 written on the screen frame 31, and FIG. 2(c) is a label. (number)
The grayscale image memory 6 labeled 1 to 6 in FIG. 2(d) is a binary image in which objects not in contact with the double-sided frame 31 are extracted.

In FIGS. 2(a) to 2(d), the binary image memory 3 to be processed in FIG. '1'
A binary image containing objects with a value of `` is stored, and among these, only three objects A, B, and C that are in contact with the screen frame 31 exist.

Here, if the processing target area is the entire area of the binary image memory 3, in order to connect the areas of objects A, B, and C into one, "1" is placed in the screen frame 31 as shown in FIG. 2(b). The value line 32 is written by the line write circuit 4. The line width at this time may be one pixel or several pixels. In this way, the objects A, B, and C that are in contact with the double-sided frame 31 are also drawn on the line 3.
2 can also be connected to one area for storing money with a value of "1". Therefore, if the labeling circuit 5 sequentially labels (numbers) each area of each object as shown in FIG. Screen frame 31 including B and C
The area of line 32 is labeled 1, the other objects are labeled 2,
The images are numbered like 3, 4, 5°6, and stored in the grayscale image memory 6. By drawing and labeling the line 32 on the boundary (screen frame) 31 between the processing target area and the non-processing target area, the object A that is in contact with the boundary (screen frame) 31 can be drawn and labeled.
, B, and C can be distinguished from regions of the object that are not in contact with the boundary. The binarization circuit 7 performs binarization processing to extract, for example, 2 or more of this labeled grayscale image.
If this is done, objects A, B, and C that are in contact with the screen frame 31 can be removed and only objects that are not in contact with the screen frame 31 can be extracted to create a binary image as shown in FIG. 2(d).

In FIGS. 2(a) to 2(d), the entire area of the binary image memory 3 is specified by the processing area specifying circuit 11 as the processing area where recognition, analysis, etc. are actually performed.

Figures 3 (a), (b), (c), and (d) show the procedure for determining whether or not the object in Figure 1 is in contact with the boundary of the processing target area (the frame of the partial rectangular area of the screen). FIG. 3(a) is a binary image memory 3 having a processing area frame 34 of a partial rectangular processing area 33 on the screen, and FIG. 3(b) is an explanatory diagram showing another embodiment. Binary image memory 3 written with 35
, FIG. 3(c) shows a grayscale image memory 6 labeled (numbered) 1 to 3, and FIG. 3(d) shows a binary image in which objects not in contact with the processing area frame 34 are extracted. Figure 3(a)-(
In d), for the case where the area of the object that is in contact with the screen frame 31 of the binary image memory 3 is distinguished from the area of the object that is not in contact with the screen frame 31 of the binary image memory 3 as shown in FIGS. Figure (a
), instead of processing the entire screen of the binary image memory 3, if a part of the screen, for example within the rectangular processing area 33, is to be processed, only a part of the object is processed in the same way as above. Since there are objects E and F that are not included in the region 33 and only a portion of which is processed, it is necessary to remove or extract these objects.

Therefore, as shown in FIG. 3(b), a line 35 is drawn in the processing area frame 34 of the binary image memory 3, and as shown in FIG. Labels 1, 2.3 are attached and stored in the grayscale image memory 6, and from this, objects that are in contact with the processing area frame 34 as shown in FIG. 3(d), E and F are removed, and only normal objects are stored. extracted 2
Value image can be changed. The processing area 33 at this time is similarly specified by the processing area specifying circuit 11.

FIG. 4 is a block diagram showing another embodiment of the image processing apparatus according to the present invention. In FIG. 4, the same reference numerals as in FIG. 1 indicate the same or corresponding parts, and 12 is a processing area designation circuit. With the configuration shown in Figure 4.

In contrast to FIG. 1, where a line with a value of 1111+ is written on the boundary (screen frame) 31 of the processing target area of the binary image memory 3 to be processed, in order to eliminate the time to write this line, the binary image Boundary of processing target area of memory 3 (screen frame)
31, a line with a value of ``1'' is written by the line writing circuit 4, and an image obtained by converting the video signal from the television camera 1, etc. into a binary value by the binarization circuit 2 is stored in the binary image memory 3. However, in order to prevent the value 'O'' from being written on the line written in the screen frame 31, it is necessary to set the processing range for writing the binary image to an area excluding the line. For this reason, the processing area designation circuit 12 specifies in advance, to the binarization circuit 2, an area excluding the lines written in the screen frame 31 of the binary image memory 3 by the line writing circuit 4, and outputs the binarization circuit 2. The line having a value of "1" is not erased by the image data. Other details are the same as in FIG.

FIGS. 5(a) and 5(b) are explanatory diagrams showing an example of the processing procedure for determining whether or not the object in FIG. 4 is in contact with the boundary (screen frame) of the processing target area. (a) shows the binary image memory 3 in which a line 32 is written in the screen frame 31 in advance,
Figure (b) shows the binary image memory 3 in which the binary image is stored in the area excluding the line 32. The rest are shown in Figure 2 (c) and (d).
). In FIGS. 5(a) and 5(b), if the processing target area of the binary image memory 3 specified by the processing area specifying circuit 11 is the entire screen, two
A line 32 with a value of 11117 is written in the screen frame 31 of the value image memory 3 in advance by the line writing circuit 4, and this 2
The output of the binarization circuit 2 by the television camera 1 is written to the value image memory 3 in the area of the write processing range excluding the line 32 specified for the binarization circuit 2 by the processing area designation circuit 12 as shown in FIG. 5(a). Write image data. Others are shown in Figure 2 (Q), (
This is the same as the process d). In addition to achieving the same effect as in FIGS. 1 and 2, this also effectively eliminates the time required to write to line 32.

In the above embodiments, all processing target areas are rectangular, but similar processing can be performed on any arbitrary shape processing target area by drawing a line along the boundary between the processing target area and the non-processing target area. The same effect can be obtained.

According to the above embodiment, the circuit is configured to draw a line on the boundary of the processing target area for the processing target image, and the labeling circuit and binarization circuit used in boat fishing, etc., and these functions are It can be configured with both hardware and software, and by writing lines on the boundaries of the processing target area of the binary image memory and labeling them, it is possible to identify objects that are in contact with the boundaries of the processing target area. Various types of image processing can be performed by quickly distinguishing between objects that are not in contact, regardless of the number of objects.

〔Effect of the invention〕

According to the present invention, objects that are in contact with the boundary between the image processing target area and the non-processing target area can be removed or extracted at high speed and independent of the number of objects. This has the effect of enabling high-speed and versatile processing, such as when the inspection time for an object to be inspected is fixed.

[Brief explanation of the drawing]

FIG. 1 is a configuration block diagram showing one embodiment of an image processing apparatus according to the present invention, FIGS. Figures (a) to (d)
) is a schematic explanatory diagram showing another example of each processing procedure,
FIG. 4 is a block diagram showing another embodiment of the image processing apparatus according to the present invention. FIG. 7 is an explanatory diagram illustrating each processing procedure of the system, FIG. 7 is an explanatory diagram illustrating object coordinate discrimination processing, and FIG. 8 is an explanatory diagram illustrating the results of label-by-label discrimination processing. 1...TV camera, 2...binarization circuit, 3...2
Value image memory, 4... Line writing circuit, 5... Labeling circuit, 6... Grayscale image memory, 7... Binarization circuit, 8... Density histogram extraction circuit, 9... Image processing circuit, 10... recognition circuit. 11.12... Processing area designation circuit, 31... Screen frame, 32... Line, 33
... Processing area, 34... Processing area frame, 35... Line.

Claims (1)

[Claims] 1. A binary image memory that binarizes and pixelizes and stores image signals of a plurality of objects to be inspected, and a processing area specification that specifies a processing target area in the space of the binary image memory. means, line data writing means for writing line data on the boundary between a processing target area and a non-processing target area of the space of the binary image memory specified by the processing area specifying means; A labeling means for labeling binary image data and line data of an object to be inspected, a grayscale image memory for storing a grayscale image labeled by the labeling means, and a grayscale image memory. an image processing apparatus comprising means for extracting only labels other than the labels containing the line data or labels containing the line data from the gray scale images stored in the gradation image as objects to be image processed and subjecting them to image processing. 2. The line data writing means is the object to be inspected.
2. The image processing apparatus according to claim 1, wherein said line data is written in said binary image memory into which value image data has been written. 3. The line data writing means writes the line data in the binary image memory in advance, and the binary image memory writes the line data of the object to be inspected to an area other than the line data written by the line data writing means. The image processing device according to claim 1, wherein binary image data is written.