JPH06118019A - Quality inspecting device - Google Patents

Abstract

PURPOSE:To precisely inspect the quality state of a colorchanging surface by quantizing a video signal, integrating each signal vertically to the color changing direction to provide a series of parameters, and determining its peak. CONSTITUTION:A film 10 is exposed to an illumination 11, and the transmitted light is picked up by a television camera 12 and quantized by an A/D converter 21 to form a digital image, which is then inputted to an image memory 22. On the basis of this image, the quality of a color transitional part on the surface is judged by a CPU 23 and transmitted from an output part 30 to the outside. To the image data, each signal in N-direction (color transitional direction) is integrated in M-direction to provide a one-dimensional signal, its intermediate density value is taken as an observation start point to determine a regression straight line from a plurality of points including this point, the square sum of shift quality between the straight line and each point is calculated, and the viewpoint is successively shifted to provide a series of parameters. The peak of this series is determined, and a plurality of predetermined points on both sides of the peak are used as input signals to a neural network to judge its rank.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a quality inspection device for inspecting the quality of the color change state of the surface of a film or the like.

[0002]

2. Description of the Related Art Conventionally, there is a method of inspecting for unevenness occurring on a uniform surface by dividing an image pickup area into small areas and comparing the uniformity with neighboring areas (Japanese Patent Laid-Open No. 63-2.
00278).

[0003]

However, the prior art has the following problems. It is not possible to inspect the state of the object to be inspected, which does not have uniformity such as color change.

It is impossible to make a delicate rank determination that matches a human sense only by comparing with a simple threshold value.

The present invention determines the quality condition of a surface that changes color.
It is an object of the present invention to provide a quality inspection device that conforms to human sensitivity and inspects with high accuracy and certainty.

[0006]

According to a first aspect of the present invention, there is provided a quality inspection device for imaging a surface of an object to be inspected and determining a quality state of the color change by a neural network. The video signal from the target is quantized, each signal is integrated in the color change vertical direction, the square sum of the deviation amount from the regression line is calculated at several points from the point of interest, and the series of the above parameters is set to the point of interest. The peaks of the above series are obtained by shifting, and a predetermined number of points on both sides of the peaks are used as input signals to the neural network.

According to a second aspect of the present invention, there is provided a quality inspection device for imaging the surface of an object to be inspected and determining the quality state of the color change by a neural network. Quantization, each signal is integrated in the color change vertical direction, the square sum of the deviation amount from the regression line is calculated at several points from the point of interest, and the series of the above parameters is obtained by shifting the point of interest. The sum of the series, the peak value, the half-value width, and the difference in the distances from the peak positions of the two points that are the half-values are used as input signals to the neural network.

However, the description of the "neural network" in the present invention is as follows (1) to (4).

(1) The neural network has the structure shown in FIG.
It can be roughly classified into two types of mutual coupling networks shown in (B). The present invention may be configured by using either of both networks, but the hierarchical network is more useful because a simple learning algorithm as described later has been established.

(2) Network Structure As shown in FIG. 6, the hierarchical network has a hierarchical structure including an input layer, an intermediate layer, and an output layer. Each layer is composed of one or more units. The coupling is only forward coupling such as input layer → middle layer → output layer, and there is no coupling within each layer.

(3) Unit structure The unit is a model of a brain neuron as shown in FIG. 7, and the structure is simple. Receive input from other units,
The sum is taken and converted by a certain rule (conversion function), and the result is output. A variable weight that represents the strength of the connection is attached to each of the connections with other units.

(4) Learning (Back Propagation) Learning a network is to bring an actual output closer to a target value (desired output). Generally, the conversion function and weight of each unit shown in FIG. Is learned by changing.

As a learning algorithm, for example, Rumelhart, DE, McClelland, JL and the PDP Re
search Group, PARALLEL DISTRIBUTED PROCESSING, the
Backpropagation described in MIT Press, 1986. can be used.

[0014]

When the quality state of the color change on the surface of the object to be inspected is judged by the neural network, the video signal from the inspection object is quantized, and each signal is integrated in the color change vertical direction, and then the neural network Since the above integration result is used as the input data, it is possible to reliably and accurately inspect the quality state of the surface where the color changes, in conformity with human sensitivity.

[0015]

FIG. 1 is a block diagram showing a first embodiment, FIG. 2 is a schematic diagram for explaining a point of interest in a one-dimensional signal, FIG. 3 is a schematic diagram showing a shift of a deviation amount from a regression line, and FIG. Is a schematic diagram illustrating input parameters in the second embodiment, FIG. 5 is a schematic diagram showing a neural network, FIG. 6 is a schematic diagram showing a hierarchical neural network, and FIG. 7 is a schematic diagram showing a structure of a unit.

(First Embodiment) (See FIGS. 1 to 3) FIG. 1 is a block diagram of an apparatus for inspecting a shaded film for laminated glass. This film is semi-transparent because it has extremely minute irregularities on the surface, and is partially colored, and the color gradually becomes lighter in one direction and becomes colorless. In the present invention, the changing state of the color transition portion is inspected.

An illumination 11 is applied from below to a film 10 as an object to be inspected, and the transmitted light is transmitted to the television camera 1.
The image is captured by 2.

In the A / D converter 21, for example, 8 bits (2
Quantization is performed with 56 gradations to create a digital image of M * N pixels, and the digital image is input to the image memory 22.

Based on this input image, the CPU 23
The quality of the color transition portion on the surface is determined by and is transmitted from the output unit 30 to the outside.

The flow until the quality judgment is shown below. For the image data of M * N pixels, each signal in the N direction (corresponding to the color transition direction) is integrated in the M direction to obtain a one-dimensional signal.

[0021]

[Equation 1]

The intermediate density value of the one-dimensional signal is found and used as the starting point of interest (FIG. 2), and several points (for example, 10
The regression line is obtained from (points), the square sum of the deviation amount of each point from the regression line is calculated, and the point of interest is sequentially shifted to obtain a series of parameters.

The peak of this series is obtained, and a predetermined number of points (for example, 32 points) on both sides of the peak are used as input signals to the neural network (see FIG. 3) to determine the rank.

The neural network is a three-layer hierarchical network (see FIG. 6). The input layer has the same number of units as the number of parameters, and the output layer has the same number of ranks to be determined. This network is preliminarily learned by back propagation so that the output unit corresponding to the rank with respect to the input is 1, and the others are 0.

(Second Embodiment) (Refer to FIG. 4) The second embodiment uses the same quality inspection apparatus as that shown in FIG. 1 of the first embodiment. The flow up to is different.

The flow until the quality judgment is shown below. For the image data of M * N pixels, each signal in the N direction (corresponding to the color transition direction) is integrated in the M direction to obtain a one-dimensional signal.

[0027]

[Equation 2]

An intermediate density value of the one-dimensional signal is found and set as a starting point of interest (FIG. 2), and several points including that point (for example, 10
The regression line is obtained from (points), the square sum of the deviation amount of each point from the regression line is calculated, and the point of interest is sequentially shifted to obtain a series of parameters.

The sum P1 of this series, the peak value P2, the half value width P3, and the difference P4 of the distances from the peak positions of the two half values are obtained, and these are used as input signals to the neural network (see FIG. 4). Determine the rank.

The neural network is a three-layer hierarchical network (see FIG. 6), the input layer is 4 units corresponding to the number of parameters, and the output layer is the same as the number of ranks to be judged. This network is preliminarily learned by back propagation so that the output unit corresponding to the rank with respect to the input is 1, and the others are 0.

In the practice of the present invention, it is clear that the same result can be obtained even if a line sensor is used for imaging the surface.

[0032]

As described above, according to the present invention, it is possible to reliably and accurately inspect the quality condition of the surface where the color changes, in conformity with human sensitivity.

[Brief description of drawings]

FIG. 1 is a block diagram showing a first embodiment.

FIG. 2 is a schematic diagram illustrating a point of interest in a one-dimensional signal.

FIG. 3 is a schematic diagram showing a transition of a deviation amount from a regression line.

FIG. 4 is a schematic diagram for explaining input parameters in the second embodiment.

FIG. 5 is a schematic diagram showing a neural network.

FIG. 6 is a schematic diagram showing a hierarchical neural network.

FIG. 7 is a schematic diagram showing a structure of a unit.

[Explanation of symbols]

 10 film (inspection object) 11 illumination 12 TV camera 21 A / D converter 22 image memory 23 CPU 30 output unit

Claims (2)

[Claims] 1. A quality inspection apparatus for imaging the surface of an object to be inspected and determining the quality state of the color change by a neural network, wherein a video signal from the inspection object is quantized and each of the signals is quantized. Color change Integral in the vertical direction, calculate the sum of squares of deviations from the regression line at several points from the point of interest, obtain the series of the above parameters by shifting the points of interest, find the peak of the above series, The quality inspection device is characterized in that a predetermined number of points are input signals to the neural network. 2. A quality inspection apparatus for imaging the surface of an object to be inspected and determining the quality state of the color change by a neural network, wherein a video signal from the inspection object is quantized and each of the signals is quantized. Color change Integral in the vertical direction, calculate the sum of squares of deviations from the regression line at several points from the point of interest, and obtain the series of the above parameters by shifting the point of interest. A quality inspection device characterized in that the difference between the distances from the peak positions of two points of the price range and the half value is used as an input signal to the neural network.