JP2023120760A - PRINT QUALITY EVALUATION DEVICE AND PRINT QUALITY EVALUATION METHOD - Google Patents

Abstract

To provide a print quality evaluation device and a print quality evaluation method capable of objectively and correctly evaluating the quality of print applied to a print object.SOLUTION: A print quality evaluation device EA for evaluating the quality of print applied to a print object comprises: image acquisition means 21 for acquiring an image obtained by capturing a print image printed on the print object; luminance value acquisition means 22 for acquiring a luminance value of the image from the image acquired by the image acquisition means 21; skewness calculation means 23 which applies the luminance value acquired by the luminance value acquisition means 22 to skewness being a roughness parameter and calculates the skewness from the luminance value; and evaluation means 24 which evaluates the quality of print on the basis of the skewness calculated by the skewness calculation means 23.SELECTED DRAWING: Figure 1

Description

The present invention relates to a print quality evaluation device and a print quality evaluation method.

For example, when high-speed printing is performed on an object to be printed by reducing the number of printing passes or lowering the print resolution, the print quality may deteriorate due to blurring of ink contours and the like. For this reason, there is known a print quality evaluation method for evaluating the print quality of printing applied to a print object (see, for example, Japanese Unexamined Patent Application Publication No. 2002-100003).

Japanese Patent Application Laid-Open No. 2020-90612

In the evaluation method described in Patent Literature 1, the print quality of printing applied to a print object is visually evaluated, so the evaluation varies depending on the subjectivity of the evaluator, and the print quality can be objectively and accurately evaluated. There is the inconvenience of not being able to

SUMMARY OF THE INVENTION It is an object of the present invention to provide a print quality evaluation apparatus and a print quality evaluation method capable of objectively and accurately evaluating the print quality of printing applied to a print object.

A print quality evaluation apparatus according to an aspect of the present invention is a print quality evaluation apparatus that evaluates the print quality of printing applied to a print object, and is a captured image obtained by imaging a print image printed on the print object. a luminance value obtaining means for obtaining the luminance value of the captured image from the captured image obtained by the image obtaining means; and the luminance value obtained by the luminance value obtaining means as a roughness. Applied to skewness which is a parameter, skewness calculation means for calculating the skewness from the luminance value, and evaluation means for evaluating the print quality based on the skewness calculated by the skewness calculation means.

In the print quality evaluation apparatus according to one aspect of the present invention, the evaluation means includes the ink density of a printed image printed on a learning print target, the skewness of the luminance value of a teacher image obtained by capturing the printed image, and The printing quality may be evaluated using a trained model obtained by machine learning using the evaluation result of the printing quality of the printing applied to the printing object for learning as teacher data.

A print quality evaluation method according to an aspect of the present invention is a print quality evaluation method for evaluating the print quality of printing applied to a print object, and is a captured image obtained by imaging a print image printed on the print object. a luminance value obtaining step of obtaining a luminance value of the captured image from the captured image obtained in the image obtaining step; and a roughness of the luminance value obtained in the luminance value obtaining step. A skewness calculation step of applying skewness, which is a parameter, to calculate the skewness from the brightness value, and an evaluation step of evaluating the print quality based on the skewness calculated in the skewness calculation step are performed.

According to one aspect of the present invention, the skewness, which is a roughness parameter, is calculated from the luminance value of a captured image obtained by capturing a print image printed on a print target, and the print quality is evaluated based on the skewness. It is possible to objectively and accurately evaluate the printing quality without changing the evaluation depending on subjectivity.

1 is an explanatory diagram of a print quality evaluation system according to one embodiment; FIG. FIG. 4 is an explanatory diagram of a print quality evaluation method according to one embodiment; The figure which shows skewness and an evaluation result. FIG. 4 is an explanatory diagram of a method of generating a learned model for evaluating print quality;

An embodiment of the present invention will be described below with reference to the drawings.
[Device configuration]
In FIG. 1, the print quality evaluation apparatus EA is an apparatus for evaluating the print quality of printing applied to a printing object such as printing paper or printing film, and is composed of a computer such as a personal computer or a server. . In addition, print quality refers to the required definition, the actual printing definition for color development, and the degree of color development. includes), the print quality is determined to be good. In addition, poor color development is caused by segregation of ink pigments, use of various inks, differences in ink wettability, and the like.
The print quality evaluation apparatus EA includes storage means 10, processing means 20, and operation means 30. Printing means 40, imaging means 50, and output means 60 constitute a print quality evaluation system EA1.

The storage unit 10 is configured by a memory, a hard disk, etc., and stores various programs for controlling the print quality evaluation apparatus EA and the print quality evaluation system EA1.
In this embodiment, the storage unit 10 also stores the skewness Rsk threshold used to evaluate the print quality.

The processing means 20 is composed of a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), and includes image acquisition means 21, luminance value acquisition means 22, skewness calculation means 23, and evaluation means 24. ing.

The image acquisition unit 21 acquires from the image pickup unit 50 a captured image obtained by capturing a print image printed on a print target. Examples of printed images include images, characters, patterns, identifiers, and test print patterns.

The brightness value acquiring means 22 acquires the brightness value of the captured image from the captured image acquired by the image acquiring means 21 .

The skewness calculation means 23 applies the luminance value acquired by the luminance value acquisition means 22 to the skewness Rsk, which is the roughness parameter, and calculates the skewness Rsk from the luminance value. The skewness Rsk is calculated by the following formula 1, where Z(x) is the roughness curve, l is the reference length of the roughness curve, and Rq is the square root height of the roughness curve at the reference length.

The evaluation unit 24 evaluates print quality based on the skewness Rsk calculated by the skewness calculation unit 23 .

The operation means 30 includes a keyboard, an operation panel, a touch panel, a mouse, various switches, a microphone for voice input operation, etc., and can input operation signals from various operations to the print quality evaluation apparatus EA and the print quality evaluation system EA1. ing. For example, the ink density for printing on the object to be printed is set via the operation means 30, and the operation signal is sent to the processing means 20 and the printing means 40 together with the set value of the ink density.

The printing means 40 includes an inkjet printer, a laser printer, a thermal printer, a dot printer, an offset printing machine, a letterpress printing machine, an intaglio printing machine, a screen printing machine, etc., and can transmit and receive various signals to and from the processing means 20. It's becoming Further, the printing means 40 is configured such that the number of printing passes and the printing resolution can be changed via the operation means 30 .

The imaging means 50 is composed of a camera, a photographing device, a microscope with an imaging function, an imaging sensor, etc., and is capable of transmitting and receiving captured images and various signals to and from the processing means 20 .

The output means 60 is composed of a display device such as a display or a panel, a notification device such as an indicator lamp or a speaker, and the like, and outputs the evaluation result by the print quality evaluation device EA on a screen, or outputs it by lighting, sound, or the like. It is designed to

[Print quality evaluation method]
Taking as an example the case of the print quality evaluation system EA1 including the print quality evaluation apparatus EA described above, the print quality evaluation method performed in the following procedure shown in FIG. 2 will be described.
First, after the user of the print quality evaluation system EA1 (hereinafter simply referred to as the “user”) sets the ink density for printing on the print target via the operation means 30, the print quality evaluation system EA1 , a signal for starting automatic operation is input through the operating means 30 . Next, when the user or transport means (not shown) such as an articulated robot or a belt conveyor places the object to be printed at a predetermined position, the processing means 20 drives the printing means 40 to print the object with the set ink density. An object is printed (step ST11). After that, the processing means 20 drives the image capturing means 50 to capture the print image printed on the print object (step ST12). At this time, the printed images printed with the number of passes and resolution that are likely to be evaluated as good in print quality are not captured, and the number of passes and resolution that are less than a predetermined value that may be evaluated as poor in print quality are not captured. You may make it image the printing image printed by. Also, the number of passes and the predetermined values of the resolution may be set according to the print target and the printing means 40 .

Next, the image acquiring means 21 acquires the captured image of the print image from the imaging means 50 (step ST13). Then, the brightness value acquiring means 22 acquires the brightness value of each pixel of the captured image from the captured image acquired in step ST13 (step ST14). In the case of the present embodiment, the brightness value acquisition unit 22 acquires the brightness value of each pixel after performing grayscale processing on the captured image. Next, the skewness calculator 23 calculates the skewness Rsk from the luminance value acquired in step ST14 (step ST15).

After that, the evaluation means 24 evaluates the print quality based on the skewness Rsk calculated by the skewness calculation means 23, and outputs the evaluation result to the output means 60 (step ST16). In the case of this embodiment, the evaluation unit 24 evaluates print quality by comparing the calculated skewness Rsk with the threshold value stored in the storage unit 10 . The evaluation unit 24 also divides the print quality into two levels and determines whether the print quality is good (accepted) or the print quality is poor (failed). Next, the output means 60 outputs the print quality evaluation result and displays it on the display device, turns on the notification device, or emits sound from the notification device to notify the user (step ST17).

Here, when printing is performed so that the area of the base to which ink is not adhered in the printed image is equal to the area of the ink adhered portion where ink is adhered, the ink on the ink adhered portion does not maintain the dot shape. For example, the base and the ink-adhered portion are clearly separated. In this case, the histogram of luminance values shows a bimodal shape with two peaks away from the normal distribution, and the value of skewness Rsk moves away from zero. Therefore, if |Rsk|>threshold, the print quality is evaluated as good.

On the other hand, even if printing is performed so that the area of the base where ink is not adhered and the area of the ink adhered portion are the same, if the ink bleeds, a gradation derived from the ink is formed on the base and the ink adhered portion becomes the same. , and the boundary between the base and the ink-adhered portion is no longer clearly separated. Such a state tends to appear more conspicuously during high-speed printing in which the number of passes is reduced. In this case, the histogram of luminance values is close to a normal distribution with one peak, and the value of skewness Rsk approaches zero. Therefore, if |Rsk|≈0, the print quality is evaluated as poor.

Also, if the skewness Rsk is excessively large, for example, the ink density is too high, or the ink adheres excessively despite the appropriate ink density, or the ink density is too low, or the ink density is not appropriate. In spite of this, there is a possibility that the area of the base to which the ink is not adhered or the area of the ink-adhered portion is excessively large because the ink is extremely poorly adhered. Therefore, if |Rsk|>>0 (if |skewness Rsk| is sufficiently larger than zero), it is evaluated as poor printability.

In the present embodiment, when the absolute value of the skewness Rsk is equal to or greater than a first threshold greater than zero and equal to or less than a second threshold greater than the first threshold, the printability is evaluated to be good. , the printability is evaluated as poor. Specifically, the first threshold is set to 0.1, and the second threshold is set to 0.5. .1 or |Rsk|>0.5 is evaluated as poor printability.

[Evaluation example]
A sample of a polyvinyl chloride film was used as an object to be printed, and the print quality was evaluated.
First, the same color photograph was printed on the samples with an inkjet printer in different numbers of passes. At this time, it is preferable to adjust the ink density so that the area of the base to which ink is not attached and the area of the ink-attached portion in the printed image of the printed color photograph are equal. was designated as CY120.

Next, after visually confirming the printing quality of the color photographs printed on the samples, a partial region of each color photograph was photographed with a digital optical microscope at a magnification of 100 times. After that, each captured image was subjected to gray scale processing, and the luminance value of each pixel of the captured image was obtained from the image data as a vertical, horizontal, or arbitrary direction line profile. Then, the skewness Rsk of the luminance value is calculated for each line profile using Equation 1, and the skewness Rsk obtained from each line profile is averaged to obtain the skewness Rsk of the luminance value of the entire captured image. Table 1 and FIG. 3 show the number of passes of printing performed on the sample, the skewness Rsk of the luminance value, and the results of visually confirming the quality of printing.

As shown in Table 1 and FIG. 3, 24-pass and 48-pass printing, which satisfies 0.1≦|Rsk|≦0.5 and is evaluated as having good print quality, is also visually confirmed to have good print quality. 12-pass printing, which is evaluated as poor print quality with |Rsk|>0.5, was visually confirmed to be poor print quality.

According to the embodiment described above, the skewness Rsk, which is the roughness parameter, is calculated from the luminance value of the captured image obtained by capturing the print image printed on the print target, and the print quality is evaluated based on the skewness Rsk. , the print quality can be evaluated objectively and accurately without changing the evaluation depending on the subjectivity of the evaluator.

Further, for example, since the print quality can be evaluated when high-speed printing is performed on the print target by reducing the number of passes or lowering the resolution, it is possible to determine whether high-speed printing is possible.

As described above, the best configuration, method, etc. for carrying out the present invention are disclosed in the above description, but the present invention is not limited thereto. That is, although the present invention has been particularly illustrated and described primarily with respect to certain embodiments, it is understood that there may be modifications to the above-described embodiments without departing from the spirit and scope of the invention. Various modifications can be made by those skilled in the art in terms of materials, quantity, and other detailed configurations. In addition, the descriptions that limit the shape, material, etc. disclosed above are exemplified to facilitate understanding of the present invention, and do not limit the present invention. The description by the name of the member that removes some or all of the limitations such as is included in the present invention.

For example, the storage means 10 may be built in the print quality evaluation apparatus EA, or may be of a type externally attached to the print quality evaluation apparatus EA.
The storage unit 10 may store the learned model when the evaluation unit 24 uses the learned model by machine learning to evaluate the print quality of the print target.

The image acquisition unit 21 may directly acquire the captured image of the print image printed on the printing object from the imaging unit 50, or may not directly acquire it from the imaging unit 50. For example, the image may be captured by the imaging unit 50. The captured image may be acquired from an image storage means such as a server or database in which images are stored.

The brightness value acquisition unit 22 may acquire the brightness value after performing grayscale processing on the captured image, or may acquire the brightness value without performing grayscale processing on the captured image.

The evaluation unit 24 sets the skewness Rsk threshold value for evaluating the print quality (print quality pass/fail) to a value other than the value of the embodiment, or divides the print quality into three or more levels for evaluation according to the skewness Rsk value. For example, when |Rsk|≦0.35, the print quality is excellent (passed), and when 0.35<|Rsk|≦0.5, the print quality is good (passed). , If |Rsk|>0.5, it may be evaluated as poor print quality (rejected), or the range |Rsk|=0 to 0.8 is divided into four, for example, every 0.2, The print quality may be evaluated in four stages, or the value of the skewness Rsk may be directly output as the evaluation result.
The evaluation means 24 may change the threshold value of the skewness Rsk according to the ink density.

The evaluation unit 24 may use a trained model machine-learned using the skewness Rsk and the ink density as feature amounts, and may evaluate print quality based on the skewness Rsk calculated by the skewness calculation unit 23 . That is, in the above embodiment, the skewness Rsk calculated in step ST15 is compared with the threshold value in step ST16 to evaluate print quality, whereas the skewness Rsk calculated in step ST15 and the ink density are evaluated in step ST16. You may make it input into a trained model and make it evaluate print quality.

The learned model includes the ink density of the print image printed on the learning print object, the skewness Rsk of the luminance value of the teacher image that captured the print image, and the print image printed on the learning print object. The evaluation results of printing quality obtained by visual confirmation are used as teacher data for machine learning, and are generated by the following procedure shown in FIG. 4 .

First, print objects of various types and compositions are prepared for learning, and printing is performed on these print objects for learning (step ST21). The printing may be performed by the printing means 40 or may be performed by means other than the printing means 40, and the shape, size, color, etc. of the printed image to be printed on the object to be printed are not particularly limited. It is preferable to adjust the ink density so that the area of the base to which ink is not attached and the area of the ink-attached portion are approximately the same.

Next, the printing quality of the print image printed on the learning print object is visually confirmed, and the print quality of the learning print object is evaluated (step ST22). After that, a printed image of the learning printing object is picked up and used as a teacher image (step ST23). The imaging may be performed by the imaging means 50 or may be performed by something other than the imaging means 50 . Next, the brightness value of each pixel is acquired from the teacher image captured in step ST23 (step ST24), and skewness Rsk is calculated as a feature amount from these brightness values (step ST25). Then, machine learning is performed using the ink density of the print image printed on the learning print object, the skewness Rsk calculated from the teacher image, and the evaluation result of the print quality evaluated in step ST22 as teacher data. A trained model is generated that inputs the ink density of the printed image printed on the object and the skewness Rsk of the brightness value of the captured image and outputs the print quality (step ST26). In the generation of the trained model, the execution order of step ST22 and steps ST23-25 is not particularly limited. You may implement step ST22 after implementing. Various well-known techniques such as neural network, support vector machine, nearest neighbor method, random forest, stochastic gradient method, and kernel approximation can be used as specific machine learning methods. and is not particularly limited.

The operation means 30 may be configured to be separable from the print quality evaluation apparatus EA, or may be configured to be inseparable.
The operation means 30 may or may not be provided in the print quality evaluation apparatus EA or the print quality evaluation system EA1. or the print quality evaluation system EA1.

The printing means 40 may or may not be provided in the print quality evaluation device EA or the print quality evaluation system EA1, and if not provided, can communicate with the print quality evaluation device EA or the print quality evaluation system EA1. An external printing device may be used to print on the object to be printed.

The imaging unit 50 may capture a printed image of the printing object in color, black and white, a part of the printed image, or the entire printed image. may
The imaging means 50 may or may not be provided in the print quality evaluation apparatus EA or the print quality evaluation system EA1, and if not provided, can communicate with the print quality evaluation apparatus EA or the print quality evaluation system EA1. The image acquisition means 21 may acquire a captured image captured by an external imaging device.

The output means 60 may or may not be provided in the print quality evaluation device EA or the print quality evaluation system EA1, and if not provided, can communicate with the print quality evaluation device EA or the print quality evaluation system EA1. You may output an evaluation result to a suitable external output device.

As for the ink density, a value set via the operation means 30 may be sent to the processing means 20 or the printing means 40, or the printing means 40 may directly transmit the ink density value to the object to be printed, or a bar code or QR code. The converted code (registered trademark) or the like may be read by the imaging means 50 , a bar code reader, a QR code reader, or the like and sent to the processing means 20 .

The type, material, composition, etc. of the object to be printed are not particularly limited. For example, the object to be printed includes paper, film, a substrate surface of an adhesive sheet, a print-receiving layer such as a coat layer provided on the substrate surface, a substrate surface of an adhesive sheet, and a coat provided on the substrate surface. It may be a print-receiving layer such as a layer or the like, and the material may be resin, metal, wood, ceramic, or the like.

The means and steps in the present invention are not limited in any way as long as they can perform the operations, functions or steps described for those means and steps. The process is not limited at all. For example, the image acquisition means may be of any type as long as it can acquire a captured image obtained by imaging a print image printed on a printing object. There is no limitation as long as it is a thing (other means and steps are the same).

EA... Print quality evaluation apparatus 10... Storage means 20... Processing means 21... Image acquisition means 22... Luminance value acquisition means 23... Skewness calculation means 24... Evaluation means 30... Operation means 40... Printing means 50... Imaging means 60... Output means

Claims (3)

A print quality evaluation device for evaluating the print quality of printing applied to a print object,
an image acquiring means for acquiring a captured image obtained by capturing a printed image printed on the printing object;
a luminance value obtaining means for obtaining a luminance value of the captured image from the captured image obtained by the image obtaining means;
skewness calculating means for applying the luminance value obtained by the luminance value obtaining means to skewness, which is a roughness parameter, and calculating the skewness from the luminance value;
and evaluation means for evaluating the print quality based on the skewness calculated by the skewness calculation means. The evaluation means evaluates the ink density of the print image printed on the learning print object, the skewness of the luminance value of the teacher image obtained by imaging the print image, and the printing applied to the learning print object. 2. The print quality evaluation apparatus according to claim 1, wherein the print quality is evaluated using a trained model machine-learned using the evaluation result of the print quality as teacher data. A print quality evaluation method for evaluating the print quality of printing applied to a print object,
an image acquisition step of acquiring a captured image of a print image printed on the print object;
a brightness value acquisition step of acquiring a brightness value of the captured image from the captured image acquired in the image acquisition step;
a skewness calculation step of applying the luminance value obtained in the luminance value obtaining step to the skewness, which is a roughness parameter, and calculating the skewness from the luminance value;
and an evaluation step of evaluating the print quality based on the skewness calculated in the skewness calculation step.

Images