JPH04220778A - Gradation image processor - Google Patents

Abstract

PURPOSE:To accurately measure a feature amount such as center of gravity at high speed without causing a quantization error and to enable the measurement of the feature amount without being affected by a background image part. CONSTITUTION:An image signal of the gradation image obtained through a camera 9 is inputted to an image input part 11 and binarized, and an expansion processing is conducted for the binarized image to generate an expanded image. The expanded image is stored in one image memory 12a and the gradation image is stored in the other image memory 12b, and a CPU 18 sets the area subject to measurement for the gradation image from the expanded image and conducts the measurement of the feature amount.

Description

[Detailed description of the invention]

0001

[Industrial Application Field] This invention relates to gradation image processing that processes a gradation image obtained by capturing an image of an object to measure characteristic quantities such as the position of its center of gravity when measuring the shape and position of an object. Regarding equipment.

0002

[Background Art] Conventionally, in order to measure the shape and position of an object, a grayscale image obtained by imaging the object is binarized to generate a binary image, and the object in the binary image is Features such as the position of the center of gravity are measured for the image part of the object. Furthermore, when a binary image includes image portions of a plurality of objects, the binary image is subjected to a labeling process and then a feature value measurement process is performed.

0003

[Problem to be Solved by the Invention] However, when performing feature measurement processing from a binary image, quantization errors occur near the boundary between the image part of the object and the image part of the background, making it difficult to measure the feature quantities with high precision. Difficult to measure. Therefore, it has been proposed to measure the feature values from the gray scale image, but with this method, the entire gray scale image is subject to processing, so the measurement process takes time and is influenced by the background image part. There is a problem.

[0004] This invention was made with attention to the above problem, and it is possible to measure feature quantities such as the position of the center of gravity with high precision and in a short time, and moreover, it is possible to measure the feature quantities without being affected by the background image part. The purpose of this paper is to propose a possible gray scale image processing device.

[0005]

[Means for Solving the Problems] The present invention is a grayscale image processing device for measuring a feature amount by processing a grayscale image obtained by imaging an object, wherein the grayscale image is subjected to binarization processing. means for generating a binary image, means for generating an expanded image by expanding an image portion of the object in the binary image by a predetermined pixel width; The apparatus is equipped with means for processing the gray scale image and measuring feature amounts.

[0006]

[Operation] Since the measurement target area of the grayscale image is set from the dilated image obtained by dilating the binary image and the feature amount is measured,
The vicinity of the boundary between the image portion of the object and the background portion is included in the measurement target area, allowing highly accurate measurement. Furthermore, since the entire grayscale image is not subject to processing, the time required for measurement processing is shortened, and there is no influence from the background image portion.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 shows the appearance of a gray scale image processing apparatus according to an embodiment of the present invention. The illustrated apparatus includes a camera 1 and an image processing device 2, and a video monitor 3 is connected to the image processing device 2. The camera 1 is placed facing downward, and there are three objects 4 and 5 within its observation field.
, 6 are located. Camera 1 detects these objects 4, 5,
6 and outputs an image signal of a grayscale image to the image processing device 2.

FIG. 2 shows an example of the circuit configuration of the image processing apparatus 10. As shown in FIG. 3, the image input section 11 has two A
/D converters 22, 24, binarization circuit 23, and expansion processing section 2
4, and each A/D converter 22, 24 converts an analog image signal into a digital image signal with 256 tones.

The binarization circuit 23 inputs the image signal from the A/D converter 22, performs binarization processing, and outputs the binary image to the expansion processing section 24. The expansion processing unit 24 performs filtering processing on the binary image, and generates an expanded image in which the binary image is expanded by one to several pixels (one pixel in this embodiment).

FIG. 4 shows the concept of the binary image and the expanded image. In the figure, the shaded areas are black pixels, and the other areas are white pixels. In addition, 4A, 5A, and 6A represent the image parts of each object 4, 5, and 6 in the binary image, and 4B, 5B, and 6B
is the image part of each object 4, 5, 6 in the dilated image,
Each is shown below. Note that 7 is the background portion in the binary image and the expanded image.

Returning to FIG. 2, one image memory 12a stores the image data of the expanded image input from the expansion processing section 24, and the other image memory 12b stores the image data of the expanded image input from the A/D converter 2.
The image data of the gray scale image input from 5 is stored in units of one pixel. Character memory 16 is connected to video monitor 14
Stores font data for characters to be displayed. The image output section 13 converts the image data outputted from the image memories 12a, 12b and the character memory 16 into analog signals, and sends one screen worth of image signals to the video monitor 14. The video monitor 14 displays input images, calculation results, etc. using image signals from the image output section 13.

The image memories 12a, 12b and the character memory 16 are connected to an address/data bus 17, and the address/data bus 17 is connected to a CPU 18, a ROM 1
9, RAM 20, and I/O port 21 are connected to form a microcomputer. In this microcomputer, a CPU 18 decodes and executes a program stored in a ROM 19, reads and writes data to and from a RAM 20, and performs various image processing such as labeling processing and feature quantity calculation processing. The timing control section 15 works in conjunction with the CPU 18 to output timing signals for controlling input and output of data in the image input section 11, image memories 12a and 12b, image output section 13, and character memory 16.

FIG. 5 shows the concept of a labeled image obtained by performing labeling processing on the expanded image. In the diagram, 4
C is the image portion of object 4 to which the label "1" has been assigned, 5C is the image portion of object 5 to which the label "2" has been assigned, and 6C is the image portion of object 6 to which the label "3" has been assigned. The image parts are shown respectively. Note that 7C is labeled “0
” is an image portion of the background 7.

Next, the operation of the gray scale image processing apparatus having the above configuration will be explained. When the objects 4, 5, and 6 are now imaged by the camera 1, the image signals of the grayscale images are output to the image input section 11. The analog image signal of the grayscale image is sent to the A/D converter 2.
2 and 25, one of the image signals is binarized by a binarization circuit 23, and then filtered by an expansion processing section 24, and the expanded image is stored in one image memory. 12a. A/D converter 25
The image signal of the grayscale image from is stored as is in the other image memory 12b.

Next, the CPU 18 performs a labeling process on the expanded image stored in the image memory 12a, stores the image data related to the labeled image in the RAM 20, and then displays the image portions 4C and 5C of each object in the labeled image. , 6C as the measurement target area, each object 4, in the grayscale image is processed by the following formula.
Center of gravity position of image parts 5 and 6 (XG1, YG1) (XG
2, YG2) (XG3, YG3).

[0016]

[Math 1]

[0017]

[Math 2]

[0018]

[Math 3]

[0019]

[Math 4]

[0020]

[Math 5]

[0021]

[Math 6]

In the above formula, X, Y are the coordinate positions on the image, nx, ny are the number of pixels in the X-axis direction and Y-axis direction, and f
(X, Y) respectively indicate the gray scale image data of the pixel indicated by the coordinates (X, Y). Also, f1 (X, Y) is the coordinate (
This function takes a value of "1" when the label "1" is assigned to the pixel indicated by (X, Y), and takes a value of "0" when any other label is assigned. Similarly f2
(X, Y) is a label for the pixel indicated by the coordinates (X, Y).
It is a function that takes the value "1" when "2" is assigned, and "0" when any other label is assigned, and f3 (X, Y) is indicated by the coordinates (X, Y). "1" when the label "3" is assigned to the pixel,
This is a function that takes a value of "0" when any other label is assigned.

[0023]

[Effects of the Invention] As described above, in order to process a grayscale image obtained by imaging an object and measure a feature quantity, the grayscale image is binarized to generate a binary image. , generate an expanded image by expanding the image portion of the object in the binary image by a predetermined pixel width, and then process a gray scale image for the image area of the object in the expanded image to measure the feature amount. By doing so, the vicinity of the boundary between the image portion of the object and the background portion is included in the measurement target area, and highly accurate measurement becomes possible. Moreover, since the entire grayscale image is not subject to processing, the time required for measurement processing is shortened, and there is no influence from background image portions, achieving the remarkable effects of achieving the purpose of the invention.

[Brief explanation of the drawing]

FIG. 1 is an explanatory diagram showing the appearance of a gray scale image processing device according to an embodiment of the present invention.

FIG. 2 is a block diagram showing a circuit configuration of an image processing device.

FIG. 3 is a block diagram showing a circuit configuration of an image input section.

FIG. 4 is an explanatory diagram showing the concept of a binary image and an expanded image.

FIG. 5 is an explanatory diagram showing the concept of a labeling image.

[Explanation of symbols]

1. Camera 2 Image processing device 11 Image input section 18 CPU 23 Binarization circuit 24 Expansion processing section

Claims (1)

[Claims] 1. A grayscale image processing device for measuring a feature amount by processing a grayscale image obtained by imaging an object, the grayscale image being binarized to generate a binary image. means for generating an expanded image by expanding an image portion of the object in the binary image by a predetermined pixel width; and generating a feature amount by processing a gray scale image for the image region of the object in the expanded image A gradation image processing device comprising: means for measuring .