JP7650204B2 - Image inspection device, method, and program - Google Patents

Description

The present invention relates to an image inspection device, method, and program for inspecting an image for defects.

In printed matter output by a printing device, "stains" can occur when color materials such as ink or toner adhere to unintended locations. In addition, there can be cases where not enough color material adheres to the location where an image is to be formed, resulting in a "color loss" that makes the color lighter than it should be. These so-called printing defects, such as stains and color loss, reduce the quality of the printed matter. For this reason, image inspection devices have been proposed that automatically inspect printed matter for defects.

Such image inspection devices prepare a reference image (standard image) that does not contain defects in advance, and determine the presence or absence of defects based on the difference image between the reference image and the image to be inspected. Defects come in a wide variety of sizes and contrasts, and if the threshold level for detecting defects (for example, the contrast threshold for the defects to be detected) is set too strictly (low), overdetection occurs frequently, in which defects caused by noise are detected in addition to defects that should have been detected, reducing productivity. On the other hand, if the threshold level is set too loosely (high), the detection accuracy for low-contrast defects decreases.

As a method for improving defect detection accuracy without reducing productivity, for example, Patent Document 1 proposes a method of adjusting the inspection level for each area based on the expected frequency of defect occurrence. That is, Patent Document 1 differentiates defect detection performance between compensation application areas and non-compensation application areas outside the compensation application areas based on compensation position information for defective image forming elements (nozzles). In this way, by making adjustments that slightly reduce the "correct detection ability" for correctly determining defects as defects only "around the compensation position" and increase the ability to avoid false detection, it is possible to improve overall detection accuracy while maintaining correct detection ability "outside the compensation position."

JP 2018-54560 A

However, defects are not always caused by nozzle failures. In addition, the proportion of the compensation application area may be large. Therefore, there is room for improvement, especially in terms of maintaining productivity without reducing the detection accuracy of low-contrast defects.

The present invention aims to improve defect detection accuracy while maintaining productivity.

To achieve the above object, the present invention is characterized by having a first acquisition means for acquiring an image obtained by reading an image printed on a recording medium by a printing device as an image to be inspected, a second acquisition means for acquiring a reference image that serves as a standard for inspecting the image to be inspected for defects, a third acquisition means for acquiring predetermined information related to the density stability of the image from the printing device, a determination means for determining the density stability of the image in printing based on the predetermined information, a setting means for setting parameters for inspecting the image to be inspected based on the density stability, and an inspection means for inspecting the image to be inspected based on the reference image and the image to be inspected using the parameters.

The present invention makes it possible to improve defect detection accuracy while maintaining productivity.

FIG. 1 is a block diagram of a printing system. FIG. 2 is a functional block diagram for implementing the inspection process. 13 is a flowchart showing an inspection process. 11 is a flowchart showing a defect detection process. FIG. 13 illustrates an example of a filter. 13 is a flowchart showing a parameter setting process. FIG. 11 is a diagram showing history information of density difference values. 13 is a flowchart showing a parameter setting process. 13 is a diagram showing history information of density difference values for each gradation value. FIG. FIG. 13 is a diagram illustrating an example of a threshold mode selection screen.

The following describes an embodiment of the present invention with reference to the drawings.

(First embodiment)
1 is a block diagram of a printing system including an image inspection device according to a first embodiment of the present invention. The printing system 1000 is composed of an image processing device 100 as an image inspection device, a printing device 190, and a printing server 180.

In this embodiment, the image processing device 100 estimates the density stability in the printing device 190 based on the measurement value of the density sensor 193 disposed in the printing device 190. The image processing device 100 identifies the level of noise that occurs frequently based on the density stability, and automatically adjusts the detection level.

The printing server 180 generates a print job and submits the print job to the printing device 190. A number of external devices (not shown) are communicatively connected to the printing server 180 via a network. The printing server 180 may receive requests to generate print jobs, print data, etc. from these external devices.

The printing device 190 has a function of forming an image on a sheet, which is a recording medium (print paper), based on a print job submitted from the printing server 180. In addition to the offset printing method, the printing device 190 can also be applied with an electrophotographic method or an inkjet method. In this embodiment, the printing device 190 will be described assuming that it is an electrophotographic method, but is not limited to this.

The printing device 190 includes a paper feed unit 191, an interface (I/F) 196, a density sensor 193, a temperature sensor 195, and a calibration control unit 194. The I/F 196 is connected to an interface (I/F) 106 in the image processing device 100. The image processing device 100 can synchronize the processing timing of printed materials with the printing device 190 and communicate each other's operating status via the I/Fs 196 and 106.

The temperature sensor 195 measures the temperature inside the printing device 190. The calibration control unit 194 performs the density calibration function in the printing device 190 and generates a calibration completion notification indicating that the density calibration has been completed. Note that in this embodiment, it is not essential to provide the temperature sensor 195 and the calibration control unit 194.

The user sets a sheet in advance in the paper feed unit 191. When a print job is input, the printing device 190 transports the sheet set in the paper feed unit 191 along the transport path 192, forms an image on the front or both sides of the sheet, and transports it to the image processing device 100.

The printing device 190 forms a chart image on a sheet at a predetermined timing (for example, after conveying a sheet corresponding to a job), and reads this chart image with the density sensor 193. The density value read by the density sensor 193 is sent to the image processing device 100 via the I/Fs 196 and 106 each time a sheet is conveyed. The timing of obtaining and sending the density value does not matter. The manner in which the density value is used will be described later. The chart image may be formed on the conveying path 192. In that case, the conveying path 192 may have a form such as an endless conveying belt. Alternatively, the density sensor 193 may be configured as a movable type, and the chart image may be read by moving the density sensor 193.

The image processing device 100 performs an inspection process to check for image defects on a sheet, which is a printed matter on which an image has been formed by the printing device 190 and which has been transported through the transport path 192. Hereinafter, the overall process of inspecting for image defects is referred to as the "inspection process" (described later in FIG. 3), and the process of detecting each of the multiple types of image defects is referred to as the "defect detection process" (described later in FIG. 4). The defect detection process also identifies the type of defect and the defective location. The defect detection process is included in the inspection process.

The image processing device 100 includes a CPU 101, a RAM 102, a ROM 103, a main memory device 104, and an image reading device 105. The image processing device 100 also includes an I/F 106, a general-purpose interface (I/F) 107, a user interface (UI) panel 108, and a main bus 109. The image processing device 100 also includes a transport path 110 connected to the transport path 192 of the printing device 190, an output tray 111 for discharging print products that have passed inspection, and an output tray 112 for discharging print products that have been found to have defects and have failed inspection. Note that the classification of print products may be more detailed than just the two types of pass and fail image inspection.

The CPU 101 is a processor that controls the entire image processing device 100. The RAM 102 functions as the main memory, work area, etc. of the CPU 101. The ROM 103 stores a group of programs executed by the CPU 101. The main memory device 104 stores applications executed by the CPU 101, data used in image processing, etc.

The image reading device 105 is a scanner that reads one or both sides of a printed material sent from the printing device 190 on the conveying path 110 and acquires the data as image data. Specifically, the image reading device 105 reads the printed material being conveyed using one or more reading sensors (not shown) provided near the conveying path 110. The reading sensor may be provided only on one side, or may be provided on both the front and back sides of the printed material being conveyed in order to simultaneously read both sides. When the reading sensor is provided only on one side, after reading one side, the printed material being conveyed using a double-sided conveying path (not shown) on the conveying path 110 may be inverted, and the other side may be read by the reading sensor again.

The I/F 106 is connected to the I/F 196 in the printing device 190. The general-purpose I/F 107 is a serial bus interface such as USB or IEEE 1394. A user can take out data such as logs or import some data into the image processing device 100 via the general-purpose I/F 107. The UI panel 108 includes, for example, a liquid crystal display, and functions as a user interface for the image processing device 100, displaying the current status and settings to inform the user. In addition, the liquid crystal display is a touch panel type, and can accept instructions from the user by the user operating the displayed buttons.

The main bus 109 connects each part of the image processing device 100. Various parts inside the image processing device 100 and the printing system 1000 can be operated by instructions from the CPU 101 via the main bus 109. For example, the image processing device 100 can synchronously move the transport path 110, and switch whether to send the printed matter to the output tray 111 or the output tray 112 depending on the inspection results. Furthermore, the image processing device 100 may be equipped with a GPU (Graphics Processing Unit) in addition to the CPU.

The image processing device 100 performs an inspection process, described below, while transporting the sheet transported from the printing device 190 along the transport path 110 based on the image data on the sheet read by the image reading device 105. If the result of the inspection process is that the sheet passes the inspection, the sheet is transported to the output tray 111, and if not, the sheet is transported to the output tray 112. In this way, only those sheets whose quality has been confirmed can be collected in the output tray 111 as deliverables for delivery.

Figure 2 is a functional block diagram that mainly realizes the inspection processing in the image processing device 100. To realize the inspection processing, the image processing device 100 has an image acquisition unit 201, a processing selection unit 202, a parameter setting unit 203, a detection processing unit 204, and a result output unit 205. These functional units are mainly realized by the cooperation of the CPU 101, RAM 102, ROM 103, main memory device 104, and I/F 106.

The image acquisition unit 201 acquires a reference image stored in the RAM 102 or the main memory device 104 and an image to be inspected. Here, the reference image represents a correct image to be compared with the image to be inspected, and is a reference image that serves as a reference for inspecting the presence or absence of defects in the image to be inspected. The reference image is, for example, image data read by the image reading device 105 from a printed matter that has been confirmed to have been printed normally by the printing device 190 (or other printing device). The reference image is stored in advance in the RAM 102 or the main memory device 104 of the image processing device 100. Note that, without being limited to this, the image acquisition unit 201 may acquire a reference image held in the printing server 180 or the printing device 190, for example. In this way, when acquiring a reference image held in an external device, the image acquisition unit 201 may transmit an acquisition request to the external device and acquire the reference image in response to the request.

The process selection unit 202 selects one or more processes from among a plurality of types of defect detection processes. The parameter setting unit 203 sets the inspection parameters to be used for the selected defect detection process based on user operations acquired via the UI panel 108. The detection processing unit 204 executes the defect detection process selected by the process selection unit 202 using the inspection parameters set by the parameter setting unit 203. The result output unit 205 outputs the inspection results processed by the detection processing unit 204 to the UI panel 108. Note that instead of or in addition to outputting the inspection results to the UI panel 108, the result output unit 205 may output the inspection results to an external device communicatively connected to the image processing device 100 via a network.

The image acquisition unit 201 is an example of a first acquisition means that acquires an image obtained by reading an image printed on a sheet (recording medium) by the printing device 190 as an image to be inspected. The image acquisition unit 201 is also an example of a second acquisition means that acquires a reference image (standard image). The parameter setting unit 203 is also an example of a third acquisition means that acquires a density value (predetermined information) read from the chart image by the density sensor 193. The parameter setting unit 203 is also an example of a determination means that determines the density stability of an image in printing based on the density value. The parameter setting unit 203 is also an example of a setting means that sets inspection parameters when inspecting the image to be inspected based on the determined density stability. The detection processing unit 204 is an example of an inspection means that inspects the image to be inspected based on the reference image and the image to be inspected using the inspection parameters.

Figure 3 is a flowchart showing the inspection process performed by the image processing device 100. This process is realized by the CPU 101 expanding a program stored in the ROM 103 into the RAM 102 and executing it. In the following, the step number of each process is indicated by a number following the S. This process is started when an instruction to start the inspection process is issued, or is started periodically.

In S301, the process selection unit 202 and the parameter setting unit 203 execute a parameter setting process (described later in FIG. 6). In summary, first, the process selection unit 202 selects at least one defect detection process to be performed based on user input or the like. The process selection unit 202 accepts a selection of a defect detection process from the user via a selection screen (not shown) displayed on the UI panel 108. On the selection screen, for example, the type of defect can be selected, and a defect detection process for detecting the selected defect is selected. The type of defect may include any type of defect, such as a point-shaped defect, a line-shaped (streak) defect, or a result of image unevenness or a surface shape. If no user selection is made, a default defect detection process may be selected.

In the parameter setting process (S301), the parameter setting unit 203 further sets inspection parameters corresponding to each of the selected defect detection processes. That is, the parameter setting unit 203 registers the inspection parameters for performing the defect detection selected by the process selection unit 202. The inspection parameters include a filter according to the type of defect and a judgment threshold TH for determining whether or not there is a defect. The parameter setting unit 203 sets the judgment threshold TH, one of the inspection parameters, based on a density difference value calculated from information sent from the printing device 190. Details of the inspection parameter setting process will be described later with reference to FIG. 6 etc.

In S302, the image acquisition unit 201 acquires a reference image from the RAM 102 or the main memory device 104. In S303, the image acquisition unit 201 acquires an inspection target image by having the image reading device 105 read the sheet conveyed from the printing device 190. Note that the configuration may also be such that read data that has been read in advance by the image reading device 105 and is stored in the main memory device 104 is acquired as the inspection target image.

In S304, the process selection unit 202 sets the defect detection process to be executed this time from among the selected defect detection processes stored in the RAM 102 to an initial value. The initial value indicates the defect detection process to be executed first, and if there is no particular priority for the defect detection processes, they may be executed in the order of selection.

In S305, the detection processing unit 204 executes a defect detection process (described later in FIG. 4). In S306, the detection processing unit 204 determines whether or not all selected defect detection processes have been completed. If the detection processing unit 204 determines that all selected defect detection processes have not been completed, the process proceeds to S307, and if the detection processing unit 204 determines that all selected defect detection processes have been completed, the process proceeds to S308.

In S307, the process selection unit 202 changes the type of defect inspection process to unprocessed, returns the process to S305, and moves to the next defect inspection process. In S308, the result output unit 205 generates and outputs the inspection results. Specifically, the result output unit 205 displays the type of defect identified and information on the defective location as the inspection result on the UI panel 108, and ends the process shown in FIG. 3.

Figure 4 is a flowchart showing the defect detection process executed in S305 of Figure 3. The process shown in Figure 4 is a subroutine of S305, and shows the flow of one defect detection process. In this embodiment, the inspection process method described is a method of detecting defects in an image to be inspected by comparing it with a reference image that has been confirmed in advance to be free of defects.

In S401, the detection processing unit 204 aligns (matches) the reference image and the image to be inspected using a general alignment processing method. In S402, the detection processing unit 204 acquires a difference image between the reference image and the image to be inspected. The difference image here is generated, for example, by comparing the reference image and the image to be inspected pixel by pixel and acquiring the difference value of the pixel value (for example, the density value for each RGB) for each pixel. In S403, the detection processing unit 204 executes a filter process on the difference image acquired in S402 to emphasize a specific shape.

Figures 5(a) and (b) are diagrams showing examples of filters used in the filter process. Filter 500 shown in Figure 5(a) is a filter for emphasizing point-like defects. Filter 501 shown in Figure 5(b) is a filter for emphasizing line-like defects. Filters are included in the inspection parameters. The filter used in the filter process is determined according to the type of defect detection process set (selected) as the initial value in S304 of Figure 3. Therefore, when detection of point-like defects is selected as the defect detection process, the process is performed using filter 500 (Figure 5(a)). Also, when detection of line-like defects is selected as the defect detection process, the process is performed using the filter shown in filter 501 (Figure 5(b)).

The filters employed depending on the type of defect detection process are not limited to those shown in Figures 5(a) and (b). In other words, although the defect detection process has been exemplified as a process for detecting point defects and a process for detecting linear defects, any process that can detect the defect desired by the user can be applied, and the filters suitable for the process are not limited to those exemplified.

In S404, the detection processing unit 204 performs binarization processing for each pixel on the difference image that has been subjected to the enhancement processing. That is, the detection processing unit 204 compares the difference value of each pixel in the difference image with the judgment threshold TH, and sets the value of a pixel whose difference value exceeds the judgment threshold TH to "1" and the value of a pixel whose difference value is equal to or less than the judgment threshold TH to "0."

In S405, the detection processing unit 204 determines whether or not there are any pixels whose value is "1" in the image that has been subjected to the binarization process. If the detection processing unit 204 determines that there are no pixels whose value is "1", it determines that there is no defect and ends the process shown in FIG. 4. On the other hand, if the detection processing unit 204 determines that there are pixels whose value is "1", it determines that there is a defect and proceeds to S406. In S406, the detection processing unit 204 stores in RAM 102 the type of defect detection process that detected the defect this time and the coordinates of the defect in association with each other, and ends the process shown in FIG. 4.

Next, the parameter setting process executed in S301 (FIG. 6) of FIG. 3 will be described in detail. As described above, in the parameter setting process, the parameter setting unit 203 selects the defect detection process to be performed and sets the inspection parameters (filter, judgment threshold TH).

Filter processing (S403) and binarization processing (S404) are performed on the acquired difference image. Taking the process of detecting point-like defects as an example, if the shape of the filter 500 (FIG. 5(a)) is made smaller, the result is that smaller point-like defects are emphasized and become easier to detect. Furthermore, if the judgment threshold TH for the binarization process is made smaller, a smaller difference value exceeds the judgment threshold TH in the binarization process, becomes "1", and is detected as a defect. Therefore, even defects with smaller contrast can be detected. In this way, parameters related to the size of the filter and the judgment threshold TH for detection are set as inspection parameters in S301.

In this embodiment, the parameter setting unit 203 has two levels of judgment threshold TH that can be set: a first judgment threshold Th_high and a second judgment threshold Th_low. The first judgment threshold Th_high is a judgment threshold used when the noise level is high and overdetection is likely to occur. The second judgment threshold Th_low is a judgment threshold used when the noise level is low and overdetection is unlikely to occur. The second judgment threshold Th_low is lower than the first judgment threshold Th_high. Note that, although an example of two levels of judgment threshold TH will be described, the number of thresholds that can be set as the judgment threshold TH may be three or more, and may be set according to the noise level.

Figure 6 is a flowchart showing the parameter setting process executed in S301 of Figure 3.

In S601, the parameter setting unit 203 sets a filter (e.g., one shown in Figures 5(a) and (b)) corresponding to the defect type selected by the user via the selection screen displayed on the UI panel 108 as part of the inspection parameters.

In S602, the parameter setting unit 203 acquires the density values sent from the printing device 190 (density values obtained by reading the chart image with the density sensor 193) and calculates density difference values based on the density values. The density values are detected by the density sensor 193. An example of the procedure for acquiring the density values is described below.

The density value measured by the density sensor 193 is a detected density value that detects the density of an image formed by a signal of a predetermined value. The predetermined value signal here is a signal of the maximum value (100%) that can be input. In other words, the parameter setting unit 203 forms a chart image on a sheet when the input signal value is maximum. This chart image is read by the density sensor 193. Note that the chart image is formed each time a sheet based on a job is transported. The measured density value is sent to the image processing device 100 via I/Fs 196 and 106.

Next, the density difference value will be described. The density difference value is a value indicating the difference between an ideal density value previously stored in the ROM 103 and a density value sent from the printing device 190. The ideal density value is the density that should be reproduced on a sheet based on the maximum input signal value, and is the target density when implementing the calibration function installed in the printing device 190. After the parameter setting unit 203 calculates the density difference value, the process proceeds to S603.

Figures 7(a) and (b) are diagrams showing history information of density difference values. The history information is stored in RAM 102. The history information records density difference values for the most recent 20 pages. Figure 7(a) shows the history information before updating, and Figure 7(b) shows the history information after updating.

In S603, the parameter setting unit 203 updates the history information of the concentration difference value based on the concentration difference value acquired in S602. That is, the parameter setting unit 203 updates the history information by replacing the latest concentration difference value calculated in S602 with the oldest information among the concentration difference value information stored in the history information. For example, the parameter setting unit 203 deletes the concentration difference value No. 20 from the history information shown in FIG. 7(a) and sends the concentration difference value before the update sequentially downward. The parameter setting unit 203 further updates the history information shown in FIG. 7(b) by inserting the newly calculated concentration difference value "10" into No. 1.

The number of pages stored as history information is not limited to 20 pages. The number of pages stored in the history information only needs to be a sufficient amount of information in order to estimate the density stability of the printing device 190 from the density difference value, and may be set by understanding the relationship between the density difference value and density stability in advance.

In S604, the parameter setting unit 203 determines whether all of the values of the history information (density difference values of all pages) are equal to or less than the standard value. Note that the "standard value" is not limited, but in this embodiment, the density difference value immediately after calibration is used in the printing device 190. This is because the engine state similar to that immediately after calibration is considered to be a state of high density stability.

If the parameter setting unit 203 determines that all of the values of the history information are equal to or less than the standard value, it determines that the concentration stability is high, and proceeds to S605. On the other hand, if the parameter setting unit 203 determines that all of the values of the history information are not equal to or less than the standard value, it determines that the concentration stability is not high, and proceeds to S606.

In S605, the parameter setting unit 203 sets the second judgment threshold Th_low as the judgment threshold TH. In S606, the parameter setting unit 203 sets the first judgment threshold Th_high as the judgment threshold TH. After S605 and S606, the parameter setting unit 203 ends the process shown in FIG. 6.

If the history information contains a large density difference value calculated from the density values obtained each time the sheet is transported, the printing device 190 is not able to stably reproduce the same density, and the density stability is low.

In this case, it can be determined that the level of generated noise is high, so a first judgment threshold Th_high is set, which is used when overdetection is likely to occur. On the other hand, when the density difference value in the history information is continuously smaller than the standard value, the printing device 190 can stably reproduce the same density. In this case, it can be determined that the level of generated noise is low, so a second judgment threshold Th_low is set, which is used when overdetection is unlikely to occur.

In this way, the density stability of the printing device 190 is estimated and the judgment threshold TH is automatically set. The noise level that causes overdetection is identified based on the estimation of density stability, and the inspection level is appropriately varied, thereby improving the detection accuracy of low-contrast defects while suppressing a decrease in productivity.

According to this embodiment, the parameter setting unit 203 acquires from the printing device 190 a detected density value obtained by measuring a chart image by the density sensor 193 as predetermined information related to the density stability of the image. The parameter setting unit 203 updates the history information with a density difference value calculated based on the detected density value, and sets a judgment threshold value TH, which is part of the detection parameters, based on the history information (FIG. 6). The detection processing unit 204 inspects the inspection target image from an image obtained by binarizing the difference image between the reference image and the inspection target image using the judgment threshold value TH, and identifies the type of defect detection processing and the coordinates of the defective location (FIG. 4). This makes it possible to improve the defect detection accuracy while maintaining productivity.

In other words, the detection processing unit 204 sets the judgment threshold TH when the density stability is in a second state, in which the density stability is higher than that of the first state, to a lower value compared to the judgment threshold TH set when the density stability is in a first state. Therefore, since overdetection is likely to occur when the density stability is relatively low, a decrease in productivity can be suppressed by using the first judgment threshold Th_high. On the other hand, since overdetection is unlikely to occur when the density stability is relatively high, detection accuracy can be maintained even for low-contrast defects by using the second judgment threshold Th_low, which is lower than the first judgment threshold Th_high.

In addition, the comparison of the difference image between the reference image and the image to be inspected with the judgment threshold TH is performed for each pixel, so even the smallest defects can be inspected.

In addition, since concentration stability is determined based on historical information of the difference values, the evaluation of concentration stability can be stabilized.

In addition, the inspection parameters are set for each type of defect to be inspected, allowing appropriate inspection to be performed according to the type of defect.

In addition, when setting the judgment threshold TH, one of multiple types of judgment thresholds TH (first judgment threshold Th_high, second judgment threshold Th_low) prepared in advance is selected based on concentration stability, so the configuration is simple.

In addition, density stability is determined based on the difference between the ideal density value to be reproduced on the sheet based on the maximum input signal value and the detected density value. The ideal density value is the target density when performing the calibration function. Therefore, the accuracy of determining density stability is high.

In this embodiment, it is assumed that the printing device 190 prints with a single color material. However, the printing device 190 may be configured to have color materials of multiple colors and form a color image. In the case of a configuration capable of color printing, the image processing device 100 may obtain a density value for each color from the printing device 190 as predetermined information related to the density stability of the image. In this case, a chart image is formed for each color, and the density is detected for each color. Therefore, the calculation of the density difference value and the update of the history information are also performed for each color. In S604 of FIG. 6, if the parameter setting unit 203 determines that the values of the history information for all colors are equal to or less than the standard value, it determines that the density stability is high, and proceeds to S605. If the parameter setting unit 203 determines that there is a value of the history information for any color that is not equal to or less than the standard value, it proceeds to S606. The standard value may be different depending on the color.

Second Embodiment
In the first embodiment, an example was described in which a density difference value was calculated when the input signal of the printing device 190 was at a maximum value. Moreover, in the first embodiment, the image to be inspected was inspected on a page-by-page basis. However, it is more desirable to calculate a density difference value for each gradation value that the input signal can take. This is because by calculating a density difference value for each gradation value and setting a judgment threshold, it is possible to estimate a more detailed density stability according to the input gradation value. Furthermore, an image may be divided into a plurality of regions, and a judgment threshold may be set for each region. Taking these factors into consideration, a second embodiment of the present invention will be described.

In this embodiment, the parameter setting process and the history information of the density difference value are different from those in the first embodiment, but the other configurations are the same. This embodiment will be described using Figs. 8 and 9 instead of Figs. 6, 7(a) and (b).

Figure 8 is a flowchart showing the parameter setting process executed in S301 of Figure 3. Figure 9 is a diagram showing history information of density difference values for each gradation value. The execution subject and start conditions of the process shown in Figure 8 are the same as those of the process shown in Figure 6.

In this embodiment, an example is taken of a configuration in which density stability is estimated for each gradation value and for each region obtained by dividing the image region of the image to be inspected, a judgment threshold is set, and the image to be inspected is inspected. "For each gradation value" means that the signal of the specified value includes signals of two or more values, and density stability is judged for each of the two or more values. Note that the number of pixels contained in the divided regions does not matter, and in this embodiment, an example is taken of a case in which the unit of the divided regions is one pixel. Therefore, density stability is estimated and a judgment threshold TH is set for each gradation value and for each pixel, rather than for each page.

First, the processes of S801 to S806 are the same as those of S601 to S606 in FIG. 6. However, S802 to S806 are executed in order for each gradation value and for each pixel. Therefore, the density value acquired from the printing device 190 in S802 is the detected density value obtained by detecting the density of the image formed with the current gradation value (the signal of the value that is the target of the current process among the signals of the specified value), and is also the detected density value related to the current pixel. Also, in S803, as shown in FIG. 9, the parameter setting unit 203 updates the history information of the density difference value for each gradation value and for each pixel.

In this example, the input signal (tone value) is divided into four levels: 100%, 75%, 50%, and 25%, and the history information is updated for each level. The history information shown in Figure 9 is stored for each region (for each pixel in this example).

In S804, the parameter setting unit 203 determines whether all values of the history information related to the current pixel and current gradation value are equal to or less than the standard value. If the parameter setting unit 203 determines that all values of the history information related to the current pixel and current gradation value are equal to or less than the standard value, it determines that the density stability is high, and proceeds to S805. On the other hand, if the parameter setting unit 203 determines that any value of the history information related to the current pixel and current gradation value is not equal to or less than the standard value, it determines that the density stability is not high, and proceeds to S806.

In S805, the parameter setting unit 203 sets the second judgment threshold Th_low as the judgment threshold TH for the current pixel and the current gradation value. In S806, the parameter setting unit 203 sets the first judgment threshold Th_high as the judgment threshold TH for the current pixel and the current gradation value. After S805 and S806, the parameter setting unit 203 proceeds to S807.

In S807, the parameter setting unit 203 determines whether or not the processing of S802 to S806 has been completed for all gradation values for all pixels. If the parameter setting unit 203 determines that the processing of S802 to S806 has not been completed for all gradation values for all pixels, the process returns to S802. In this case, the process proceeds to the next pixel or the next gradation value. If the parameter setting unit 203 determines that the processing of S802 to S806 has been completed for all gradation values for all pixels, the process shown in FIG. 8 ends.

This embodiment can achieve the same effect as the first embodiment in terms of improving defect detection accuracy while maintaining productivity.

In particular, since the judgment threshold TH is set for each gradation value and for each pixel, it is possible to improve the accuracy of detecting defects that tend to occur only in certain gradations or in certain regions.

It is not essential to set the judgment threshold value TH for each gradation value and for each pixel. That is, the judgment threshold value TH may be set for each gradation value of the entire image region of the image to be inspected. Alternatively, the gradation value may be at one level, and the judgment threshold value TH may be set for each region (e.g., for each pixel) obtained by dividing the image region into multiple regions.

The present invention has been described in detail above based on preferred embodiments, but the present invention is not limited to these specific embodiments, and various forms within the scope of the gist of the invention are also included in the present invention. Parts of the above-mentioned embodiments may be combined as appropriate. Modifications are described below.

Figure 10 is a diagram showing an example of a threshold mode selection screen. In the explanation so far, in the parameter setting process (S301), the judgment threshold TH is automatically set based on the concentration stability. However, it is also possible to allow the user to arbitrarily set whether or not to switch the judgment threshold TH.

For example, a fixed threshold mode in which the judgment threshold TH is set to a fixed value and an automatic threshold adjustment mode in which the judgment threshold TH is automatically set can be selected by a user operation on the UI panel 108. The fixed threshold mode is a mode in which the inspection process is performed with a fixed threshold in order to unify the defect level compensated for as the deliverable.

As shown in FIG. 10, the process selection unit 202 displays a threshold mode selection screen 1001 on the UI panel 108, and allows the user to select a mode. When the automatic threshold adjustment mode is set, the processes shown in FIG. 3 described above are executed, and the judgment threshold TH is set based on the concentration stability. However, when the fixed threshold mode is set, the judgment threshold TH is set to a fixed value regardless of the concentration stability. This can improve usability for the user.

In the above embodiments, the detected density value measured on the chart image is exemplified as the specific information related to the density stability of the image, but this is not limiting. For example, the specific information may be a notification indicating that image density calibration has been completed. The calibration control unit 194 (FIG. 1) performs a density calibration function and generates a calibration completion notification indicating that density calibration has been completed. The image processing device 100 receives the calibration completion notification via the I/Fs 196 and 106. When the calibration completion notification is received, the parameter setting unit 203 determines that the density stability of the printing device 190 is high, and executes S605. This simplifies the configuration. The density stability may be determined to be high on the condition that a specific time has not elapsed since the calibration completion notification was received.

Alternatively, the specified information may be information about the temperature detected in the printing device 190. The temperature sensor 195 measures the temperature inside the printing device 190, and the image processing device 100 receives the measured temperature information via the I/Fs 196 and 106. If the received temperature information indicates a temperature within a specified range, the parameter setting unit 203 determines that the density stability of the printing device 190 is high, and executes S605. This simplifies the configuration. Note that the density stability may be determined to be high on the condition that a specified time has not elapsed since the temperature information was received.

Other Examples
The present invention can also be realized by a process in which a program that realizes one or more of the functions of the above-mentioned embodiments is supplied to a system or device via a network or a non-transitory storage medium, and one or more processors of a computer in the system or device read and execute the program. The above program and the storage medium that stores the above program constitute the present invention. The present invention can also be realized by a circuit (e.g., ASIC) that realizes one or more of the functions.

100 Image processing device 190 Printing device 201 Image acquisition unit 203 Parameter setting unit 204 Detection processing unit

Claims (15)

a first acquisition means for acquiring an image printed on a recording medium by a printing device as an inspection target image;
a second acquiring means for acquiring a reference image serving as a reference for inspecting the inspection target image for the presence or absence of a defect;
a third acquiring means for acquiring predetermined information related to density stability of an image from the printing device;
a determination unit for determining density stability of an image in printing based on the predetermined information;
a setting means for setting parameters for inspecting the inspection target image based on the density stability;
and an inspection means for inspecting the image to be inspected based on the reference image and the image to be inspected using the parameters. The parameters include a decision threshold;
The image inspection device according to claim 1, characterized in that the inspection means compares a difference image between the reference image and the image to be inspected with the judgment threshold, and determines that the image to be inspected has a defect if a pixel exceeding the judgment threshold is present. The image inspection device according to claim 2, characterized in that the setting means sets the judgment threshold value set when the density stability is in a first state to a lower value than the judgment threshold value set when the density stability is in a second state in which the density stability is higher than the first state. The image inspection device according to any one of claims 1 to 3, characterized in that the setting means sets the parameters for each type of defect to be inspected. The image inspection device according to any one of claims 1 to 4, characterized in that the setting means sets one parameter from among multiple types of parameters when inspecting the inspection target image based on the density stability. the predetermined information is a detected density value obtained by detecting the density of an image formed by a signal of a predetermined value,
6. An image inspection device according to claim 1, wherein the determining means determines the density stability based on a difference value between an ideal density value of an image formed by a signal of the predetermined value and the detected density value. The image inspection device according to claim 6, characterized in that the determination means determines the density stability based on the history of the difference values. The image inspection device according to claim 6 or 7, characterized in that the signal of the predetermined value is a signal of the maximum value that can be input. the predetermined value signal includes two or more types of value signals,
The image inspection device described in claim 6 or 7, characterized in that the judgment means judges the density stability for each of the two or more types of values, the setting means sets the parameters for each of the two or more types of values, and the inspection means inspects the image to be inspected for each of the two or more types of values. The image inspection device according to any one of claims 6 to 9, characterized in that the determination means determines the density stability for each of a plurality of regions obtained by dividing the image region of the inspection target image, the setting means sets the parameters for each of the divided regions, and the inspection means inspects the inspection target image for each of the divided regions. The image inspection device according to any one of claims 1 to 5, characterized in that the specified information is a notification indicating that image density calibration has been completed. The image inspection device according to any one of claims 1 to 5, characterized in that the specified information is information about the temperature detected in the printing device. A mode in which the parameter is set to a fixed value can be set by a user operation;
13. The image inspection device according to claim 1, wherein the setting means sets the parameter to the fixed value when the mode is set, regardless of the density stability. a first acquisition step of acquiring an image printed on a recording medium by a printing device as an inspection target image;
a second acquisition step of acquiring a reference image serving as a reference for inspecting the inspection target image for the presence or absence of a defect;
a third acquisition step of acquiring predetermined information related to density stability of an image from the printing device;
a determining step of determining density stability of an image in printing based on the predetermined information;
a setting step of setting parameters for inspecting the inspection target image based on the density stability;
an inspection step of inspecting the inspection object image based on the reference image and the inspection object image using the parameters. A program for causing a computer to execute the image inspection method described in claim 14.