JPH0438456A - Apparatus for inspecting surface state - Google Patents

Abstract

PURPOSE:To inspect the surface state of an object to be inspected by obtaining a large number of adaptation coefficients F with respect to the successively inputted image data of respective objects to be inspected to form the frequency distribution thereof and comparing the adaptation coefficient F of each object to be inspected with the threshold value determined from the mean value and standard deviation thereof. CONSTITUTION:A television camera 10 transmits a multilevel image sampled in a pixel unit to an inspection apparatus 20. A large number of adaptation coefficients F are obtained with respect to the successively inputted image data of respective objects to be inspected to form the frequency distribution thereof and the mean value Fmu and standard deviation Fsigma of the frequency distribution are calculated to determine a threshold value according to T=Fmu + Fsigma and the adaptation coefficient F calculated with respect to each object to be inspected with the threshold value T to inspect the surface state of the object to be inspected.

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention relates to a surface condition inspection device that detects surface conditions such as scratches, dust, roughness, and uneven color (shading of color tone) existing on a surface.

[Prior art] Conventionally, as a surface flaw inspection device, He was applied to the surface of an object to be inspected.
-Ne laser light is irradiated, and the presence of scratches on the surface is detected based on the degree to which it is scattered by the unevenness of the scratches.

[Problems to be Solved by the Invention] However, the above conventional surface flaw inspection apparatus using the light irradiation-scattering method has the following problems (1) to (4).

■The optical system is complicated and the device is large.

■Surface conditions such as color unevenness that are not accompanied by surface irregularities cannot be detected.

■Detection results do not necessarily match the sense perceived by the human eye.

An object of the present invention is to use a compact device configuration to reliably inspect surface conditions, including color unevenness, with a feeling similar to that of humans.

[Means for Solving the Problems] The present invention provides an imaging device that images the surface of an object to be inspected, a verification device that verifies the surface state of the object to be inspected based on the imaging result of the imaging device, and a verification device for the verification device. There is a surface condition inspection device configured to include an output device that outputs a result, and the verification device calculates a density histogram n (K) for image data captured by an imaging device, and calculates the density histogram n
(K), calculate the theoretical frequency g (K) of each concentration that follows a normal distribution with the above average value μ and standard deviation σ, and calculate the above concentration histogram n (K).
The compatibility coefficient F corresponds to the difference between the theoretical frequency g (K) and the above theoretical frequency g (K)
The calculation operation for calculating the compatibility coefficient F is performed on the image data of each inspected object that is input one after another from the imaging device, thereby obtaining a large number of compatibility coefficients F and creating their frequency distribution. The surface condition of the object to be inspected can be determined by determining the average value Fμ and standard deviation Fσ of It is designed to test the

[Action Co. According to the present invention, the following effects (1) to (4) are achieved.

■The surface condition can be detected using a versatile imaging device such as a television camera, and the device configuration can be made more compact.

Since the surface condition is detected based on the concentration distribution state of the 0 surface, the surface condition including color unevenness can be detected with a sense similar to that of humans.

■Concentration histogram n (
compatibility coefficient F corresponding to the difference between K) and the theoretical frequency g (K)
is determined, and the conformity coefficient F determined for each object to be inspected is compared using a threshold value T determined based on the average value Fμ and standard deviation Fσ of the frequency distribution, and the surface condition of the object to be inspected is verified. did. Thereby, it is possible to reliably separate whether the object to be inspected is good or bad, and to improve the accuracy of the test.

In addition, threshold values that serve as standards for verification can be automatically set.

[Example] Fig. 1 is a block diagram showing an example of the inspection device of the present invention, Fig. 2 is a schematic diagram showing image data, Fig. 3 is a flowchart showing the inspection procedure according to the present invention, and Fig. 4 is a compatibility coefficient. FIG. 2 is a schematic diagram showing the frequency distribution of .

The surface condition inspection device 1 includes a television camera 10 (imaging device)
, a verification device 20, and an output device 3o, and inspects the surface of an object to be inspected, such as a thermoplastic foam sheet, for abnormalities.

The basic operations of the surface condition inspection device are as follows (1) to (4).
It is.

(1) The surface of the foam sheet is imaged by the television camera 10.

The television camera 10 transfers a multivalued image sampled pixel by pixel to the test device 20.

(2) The verification device 20 quantizes the image data of the television camera 10 using the A/D converter 21, for example, at 8 bits (256 gradations), creates a digital image of MXN pixels, and inputs this into the image memory 22. do.

(3) Based on the image input to the image memory 22, the inspection bag W20 is inspected by the CPU 23 to see if there is any abnormality on its surface.

(4) The output device 30 displays the test results of the test device 20 and generates an alarm if necessary.

Note that as the imaging device (10), a line sensor having M spatial resolution may be used instead of the television camera. In this case, the line sensor and the object to be inspected are moved relative to each other, N groups of data are stored in the image memory.

The verification device 20 does not necessarily use the image memory 22, and the
The output data of the /D converter 21 may be input directly to the CPU 23.

However, the verification operation by the verification device 20 is as follows.
This is done as follows (see Figure 3).

(2) Obtain a density histogram n (k) for the image data of MXN pixels (k: density value, n: frequency).

When creating this density histogram n (k), depending on the size of the abnormal part predicted in advance in the test object or the sampling density by the television camera 10, it may not be necessary to use all MXN pixels input to the verification device 20. , mXn (n5M, n≦N) pixels (see Figure 2 (A)), or pixels where N is an even number (Figure 2 (B)).
) may also be used as part of the MXN pixels.

■Average each density value next to each other to make the histogram smooth. For example, the frequency n' (K) for the density value is n' (K) = In (k-2) + 2 n (K-
1) + 3 n (K) + 2 n (K+1) +
n (k+2) ko / 9
...Replace with (1).

(2) Based on the averaged density histogram n'(K), find its average value μ and standard deviation σ.

Σ k−n'(K) Σn' (K) ...(
3) ■ Calculate the theoretical frequency g (K) of each concentration according to the normal distribution N (μ, σ2) with the average value μ and standard deviation σ of the concentration histogram n ′ (K).

■Concentration histogram n' (K) and theoretical frequency g (K
) is calculated using the following formula (4) or (5).
) is calculated using the formula. However, this compatibility coefficient F is g (K
)≠0, and in equations (4) and (5), if i-bit quantization is performed, L=2421.

g (K) ... (4) g (K) ... (5) ■ The calculation operation for determining the conformity coefficient F described in (■) above is performed on the image data of each object to be inspected that is input one after another from the television camera 10. In this way, a large number of compatibility coefficients F are obtained and a frequency distribution thereof is created.

■Mean value Fμ and standard deviation Fσ of the frequency distribution obtained by ■ above
seek. Then, the threshold value T is determined by the following equation (6).

T=Fμ+cFσ (c is a constant) - (6) ■Compare the conformity coefficient F obtained for each object to be inspected with the above threshold T, F≦T: Good product F>T: Defective product ... (7) The result is output (see Figure 4).

Next, the operation of the above embodiment will be explained.

- Surface conditions can be detected using a versatile imaging device such as the television camera 10, and the device configuration can be made compact.

Moreover, the processing contents are simple, and the surface condition can be verified in a short time, and the inspection can be completed even on the conveyance line of the object to be inspected.

■Since the surface condition is detected based on the surface concentration distribution, it is possible to detect the surface condition, including color unevenness, with a sense similar to that of humans.

■Density histogram n' for a large number of image data
(K) and the theoretical frequency g (Kl), and calculate the mean value Fμ and standard deviation F of the frequency distribution.
The conformity coefficient F obtained for each object to be inspected was compared using a threshold value T determined based on σ, and the surface condition of the object to be inspected was verified. Thereby, it is possible to reliably separate whether the object to be inspected is good or bad, and to improve the accuracy of the test.

In addition, threshold values that serve as standards for verification can be automatically set.

[Effects of the Invention] As described above, according to the present invention, surface conditions including color unevenness etc. can be reliably inspected with a sense similar to that of humans using a compact device configuration.

[Brief explanation of drawings]

Fig. 1 is a block diagram showing an example of the inspection device of the present invention, Fig. 2 is a schematic diagram showing image data, Fig. 3 is a flowchart showing the inspection procedure according to the invention, and Fig. 4 shows the frequency distribution of the conformity coefficient. FIG. 10... Imaging device, 0... Verification device, 30... Output equipment.

Claims (1)

[Claims] (1) It has an imaging device that images the surface of the object to be inspected, a test device that tests the surface condition of the test object based on the imaging results of the imaging device, and an output device that outputs the test results of the test device. The verification device obtains a density histogram n(K) for the image data captured by the imaging device, and calculates the average value μ and standard deviation σ based on the density histogram n(K). The theoretical frequency g(K
) is calculated, and a fitting coefficient F corresponding to the difference between the density histogram n(K) and the theoretical frequency g(K) is calculated, and the calculation operation for calculating the fitting coefficient F is performed for each object input one after another from the imaging device. By performing this on the image data of the inspection object, a large number of conformity coefficients F are obtained and a frequency distribution thereof is created.The average value Fμ and standard deviation Fσ of the frequency distribution are determined, and the threshold value is set as T.
A surface condition inspection apparatus that verifies the surface condition of an object to be inspected by comparing the conformity coefficient F determined for each object to the above threshold T, determined by =Fμ+Fσ.