JP7443719B2 - Image inspection equipment and image inspection system - Google Patents

Description

The present invention relates to an image inspection apparatus and an image inspection system.

When printing in large quantities, the operator usually performs several trial prints and makes various adjustments, and then starts actual printing after confirming from the sample that there are no problems with the printed content. However, for some reason, color misregistration or distortion may occur in the image of the actual printed paper with respect to the sample. Therefore, in recent years, an inspection system has been provided in which a reading device such as a scanner is provided on the conveyance path after the image forming device, and an image inspection device inspects the read image obtained by reading the image of each sheet to be printed out. It became so. In this inspection, the original image of the image formed on the paper is saved as the output target image. Then, the image inspection device compares an image (read image) obtained by reading the paper printed in the actual printing with a scanner and a saved output target image.

When the read image and the output target image are compared, image defects may be detected from the read image. Types of image defects include, for example, narrow stripes or bands that appear continuously in a predetermined direction or that appear discontinuously in a predetermined direction. Such image defects are collectively referred to as streak defects. However, in the following description, the streak-like defect is also abbreviated as "streak." Streaks are defects caused by scratches or dirt on the drums and rollers of image forming devices, scanners, and other reading devices. It appears as "streak intensity") and density unevenness. Examples of the streaks include white streaks that are thinner than the original image, black streaks that are darker than the original image, and the like. Because streaks tend to occur repeatedly and are easily recognized by operators and customers, it is necessary to reliably detect streaks even during actual printing.

A technique disclosed in Patent Document 1 is known for detecting streaks. In this Patent Document 1, a second difference image is generated by taking a difference between a first difference image between an output target image and a read image, and a pixel separated by a predetermined number of pixels, and , the first number of pixels whose pixel value is larger than the first threshold value and the second number of pixels whose pixel value is smaller than the first threshold value are calculated, and the number of pixels whose pixel value is smaller than the first threshold value is calculated. A technique for determining streaks based on the ratio between the number of pixels of 1 and the number of pixels of a second type has been disclosed.

Unexamined Japanese Patent Publication No. 2017-173000

Lines appear in the sub-scanning direction or the main-scanning direction of an image formed on paper due to various factors. For example, if a charging electrode provided in an image forming apparatus is soiled with toner or the like, charging of the soiled area may not be successful, and as a result, streaks may appear in the sub-scanning direction of the image. Further, when a defect occurs in a rotating body such as a photosensitive drum, streaks appear in the main scanning direction in synchronization with the rotation period of the rotating body. Here, the streaks appearing in the read image will be explained with reference to FIG. 1.

FIG. 1 is a graph showing an example of data obtained by averaging pixel values in the sub-scanning direction (FD: Feed direction). The horizontal axis of this graph represents the main scanning position of the read image in the main scanning direction (CD: Cross direction), and the vertical axis represents the pixel value of each pixel of the read image read in G-ch (green channel). represent. This graph is obtained by averaging the pixel values of pixels in the sub-scanning direction at the same position in the main-scanning direction, based on the results of reading a flat image by a reading device such as a scanner. The following example will be described assuming that the printing direction in which images and characters are formed on paper coincides with the main scanning direction, but the same applies when the printing direction matches the sub-scanning direction. Here, it is assumed that the read image shown in FIG. 1 has two streaks in the sub-scanning direction.

Conventionally, in order to detect streaks in a read image, a method of determining the difference between the read image and the output target image has been used. If the read image and the output target image match, there is no difference, but if a streak occurs in the read image, a difference occurs near the location where the streak occurs, so the streak can be detected. However, if an image is formed with the paper slightly tilted, a positional shift will occur between the read image read from the paper and the output target image. For this reason, there is a risk that a stripe may be erroneously detected even though no stripe actually occurs in the read image.

Furthermore, even if the technology disclosed in Patent Document 1 is used, there are errors such as color conversion between the output target image and the read image, so if the difference is directly calculated, the influence of the error will be large, and there is a risk of erroneously detecting streaks. was there. Further, in the technique disclosed in Patent Document 1, when comparing the output target image and the read image to generate a difference image, the shift due to alignment is not taken into account. Therefore, if a misalignment occurs due to alignment between the output target image and the read image, there is a risk that a stripe may be erroneously detected from an area where there is actually no stripe.

The present invention was developed in view of this situation, and even if there is a misalignment between the output target image and the read image, it is possible to detect streak-like defects from the read image and judge the quality of the image. The purpose is to make it possible.

In order to achieve at least one of the above objects, an image inspection apparatus that reflects one aspect of the present invention includes an output target image that is the source of an image that an image forming apparatus forms on a recording material, and an image that is formed on a recording material. a positioning unit that aligns the read image read from the recording material, and a positioning unit that takes the difference between the shifted image obtained by shifting the read image horizontally or vertically by a predetermined number of pixels and the read image before shifting; Based on the classification threshold for classifying the difference image generated by and a change amount calculation unit that classifies the amount of change in the image formed on the recording material based on the amount of change classified based on the plurality of pixels in a second direction intersecting the first direction. A feature extracting unit extracts the feature of the streak-like defect that occurs, and detects the streak-like defect by comparing the feature with a preset defect detection threshold along the first direction. and a quality determination unit that determines the quality of the image formed on the image.
Note that the above image inspection apparatus is one aspect of the present invention, and an image inspection system that reflects one aspect of the present invention is also configured in the same manner as the above image inspection apparatus.

According to the present invention, even if there is a misalignment between the output target image and the read image, it is possible to detect streak-like defects from the read image and judge the quality of the image. Quality improves.
Problems, configurations, and effects other than those described above will be made clear by the following description of the embodiments.

It is a graph showing an example of data obtained by averaging pixel values in the sub-scanning direction. 1 is a schematic configuration diagram of an image inspection system according to an embodiment of the present invention. FIG. 1 is a block diagram illustrating a configuration example of a control system of an image forming apparatus according to an embodiment of the present invention. FIG. 1 is a block diagram showing an example of the configuration of a control system of an image inspection apparatus according to an embodiment of the present invention. FIG. 3 is a diagram illustrating an example of a read image including streaks to be detected and a classification result according to an embodiment of the present invention. FIG. 3 is a diagram showing how a streak feature is extracted from classification results according to an embodiment of the present invention. 7 is a graph showing an example of pixel values and difference values of pixels in a flat region and a non-flat region of a read image according to an embodiment of the present invention, and a classification threshold. FIG. 7 is a diagram showing an example of a change in a graph representing a difference value when a shift occurs in alignment according to an embodiment of the present invention. FIG. 3 is a diagram illustrating an example in which classification thresholds are varied according to an embodiment of the present invention. 3 is a flowchart illustrating an example of processing performed by the inspection processing device according to an embodiment of the present invention. FIG. 7 is a diagram illustrating how the range of classification thresholds is two-dimensionally expanded according to a modification of the embodiment of the present invention.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments for carrying out the present invention will be described with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functions or configurations are designated by the same reference numerals and redundant explanations will be omitted.

[One embodiment]
<Configuration of image inspection system>
By taking the difference between a pixel of interest included in a read image and a comparison pixel located near the pixel of interest, the present inventor has discovered that noise that cannot be separated from noise as shown in FIG. We have invented an image inspection device that detects streaks while minimizing the effects of density unevenness. Below, a configuration example and an operation example of an image inspection system including an image inspection apparatus capable of detecting streaks from a read image according to the present embodiment will be described with reference to FIGS. 2 to 10.

First, with reference to FIG. 2, a configuration example of an image inspection system according to an embodiment of the present invention will be described.
FIG. 2 is a schematic configuration diagram of an image inspection system 1 according to an embodiment of the present invention. Note that FIG. 2 shows elements considered necessary for explaining the present invention or related elements thereof, and the image inspection system of the present invention is not limited to the example shown in FIG. 2.

The image inspection system 1 includes an image forming device 2 and an image inspection device 3. The image forming apparatus 2 is an example of an image forming apparatus that forms an image on paper using an electrophotographic method that uses static electricity to form an image. The image forming apparatus 2 forms a color image on a sheet, for example, in a tandem format in which toner images of four colors, yellow (Y), magenta (M), cyan (C), and black (K) are superimposed. A PC (Personal Computer) 6 (see FIG. 3 described below) operated by an operator is connected to the image forming apparatus 2 via a LAN (Local Area Network) not shown. Then, a job is input from the PC 6 to the image forming apparatus 2 via the LAN. The image forming apparatus 2 performs various processes such as image forming process according to the submitted job.

First, a configuration example of the image forming apparatus 2 will be described.
The image forming apparatus 2 includes an image input section 11 having an automatic document feeder (ADF) 12 and an operation display section 13 . The image forming apparatus 2 also includes a printer section 10 having a paper feed tray 20 and an image forming section 30.

The image input unit 11 optically reads an image from a document on the document table of the ADF 12, performs A/D conversion on the read image, and generates image data. Note that the image input unit 11 can also read an image from a document on a platen glass.

The operation display unit 13 includes a display unit such as a liquid crystal panel, and an operation unit such as a touch sensor. The display section and the operation section are integrally formed as a touch panel, for example. The operation display unit 13 generates an operation signal representing the content of the operator's operation input to the operation unit, and supplies the operation signal to the control unit 50 (see FIG. 3, which will be described later). Further, the operation display section 13 displays the contents of the operation by the operator, setting information, etc. on the display section based on the display signal supplied from the control section 50. Note that it is also possible to configure the operation unit with a mouse, a tablet, etc., and to configure it separately from the display unit.

The paper feed tray 20 is a container that accommodates paper Sh on which image formation is performed in the image forming section 30. The paper feed trays 20 accommodate sheets of paper having different paper types, basis weights, and the like. The paper Sh is an example of a recording material. The image forming apparatus 2 can also form an image on a resin sheet, which is an example of a recording material. Note that in this embodiment, an example is given in which two paper feed trays 20 are provided, but the number of paper feed trays 20 may be one, or may be three or more.

The image forming apparatus 2 is provided with a conveyance path 21 that conveys the paper Sh fed from the paper feed tray 20 to the image inspection apparatus 3. The transport path 21 is provided with a plurality of transport rollers for transporting the paper Sh.

On the downstream side of the fixing unit 36 , the conveyance path 21 extends and is connected to the conveyance path 41 of the image inspection device 3 . Furthermore, the conveyance path 21 branches on the downstream side of the fixing section 36. A reversing conveyance path 22 that joins the conveyance path 21 on the upstream side of the printer section 10 is connected to one end of the branched conveyance path 21 . The reversing conveyance path 22 is provided with a reversing section 23 for reversing the paper Sh. The sheet Sh reversed by the reversing unit 23 is returned to the upstream side of the transport path 21 through the reversing transport path 22 . Further, the sheet Sh that has been reversed due to the switching of the path may be returned to the conveyance path 21 on the downstream side of the fixing section 36 and then conveyed to the image inspection apparatus 3.

The image forming section 30 includes four image forming units 31Y, 31M, 31C, and 31K for forming toner images of each color of Y, M, C, and K, and forms images on paper Sh. The image forming units 31Y, 31M, 31C, and 31K each include a charging section, an exposure section (all not shown), photosensitive drums 32Y, 32M, 32C, and 32K as image carriers, and developing sections 33Y, 33M, and 33C. , 33K.

The developing sections 33Y, 33M, 33C, and 33K generate electrostatic charges on the periphery of each photosensitive drum by irradiating each surface (outer periphery) of the photosensitive drums 32Y, 32M, 32C, and 32K with light according to the image. Form a latent image. The developing units 33Y, 33M, 33C, and 33K form toner images on the photoreceptor drums 32Y, 32M, 32C, and 32K by attaching toner to the electrostatic latent images.

The image forming section 30 also includes an intermediate transfer belt 34, a secondary transfer section 35, and a fixing section 36. The intermediate transfer belt 34 is a belt to which images formed on the photoreceptor drums 32Y, 32M, 32C, and 32K are primarily transferred. The secondary transfer unit 35 is a roller that secondarily transfers the toner images of each color that have been primarily transferred onto the intermediate transfer belt 34 onto the paper Sh that has been conveyed through the conveyance path 21 .

The fixing unit 36 is disposed downstream of the secondary transfer unit 35 in the paper transport direction, and performs a fixing process on the paper Sh supplied from the image forming unit 30 and on which a color toner image has been formed. The fixing unit 36 fixes the image transferred by the image forming unit 30 on the front side of the paper Sh by heating and pressurizing the transported paper Sh. The paper Sh on which the image has been fixed by the fixing section 36 is transported to the image inspection device 3 through the transport path 21, or is transported upstream of the printer section 10 after passing through the reversing transport path 22 and being turned upside down by the reversing section 23. It is returned to Route 21. The printer section 10 forms an image on the back side of the sheet Sh, which has been turned upside down. Thereafter, the sheet Sh subjected to the fixing process by the fixing unit 36 is conveyed to the image inspection device 3.

Next, a configuration example of the image inspection apparatus 3 will be described.
The image inspection device 3 performs an image inspection to detect streaks generated in the image formed (printed) on the paper Sh conveyed from the image forming device 2. The processing of the image formed on the paper Sh, that is, the inspection of the image by the image inspection device 3 is mainly performed by the inspection processing device 5 attached to the image inspection device 3.

The image inspection device 3 includes conveyance paths 41, 42, and 43, a switching section 44, reading sections 45a and 45b, a colorimeter 46, and conveyance paths 41, 42, and 43 for conveying the sheet Sh conveyed from the image forming apparatus 2. It has paper ejection trays 47 and 48 from which the paper sheets Sh are ejected.

The reading units 45a and 45b are each an example of an image input device such as an image sensor. The reading units 45a and 45b, for example, project light onto the surface of the paper Sh and capture reflected light from the paper Sh as image data. The reading of the image data of the paper Sh by the reading units 45a and 45b in this manner is called "reading". The reading section 45a reads the paper Sh conveyed through the conveyance path 41 from below the conveyance path 41, and the reading section 45b reads the sheet Sh conveyed through the conveyance path 41 from above the conveyance path 41. In the following description, the reading sections 45a and 45b will not be distinguished, and will be collectively referred to as "reading section 45." The reading unit 45 then outputs the captured image data to the inspection processing device 5.

The colorimeter 46 reads an image formed on the upper surface of the paper sheet Sh being transported through the transport path 41, and measures the color density (reflection density) of the image based on the image information obtained by reading the image. This is an example of a device. The colorimeter 46 is, for example, a colorimeter that can measure the intensity (spectrum) of reflected light for each wavelength of light, and measures the measured color density (reflection density), L*a*b* value, etc. Output. The colorimeter 46 uses, for example, a scanner (line sensor) in which a plurality of sensors (photoelectric conversion elements) (not shown) are arranged one-dimensionally over the entire paper width direction (direction orthogonal to the paper conveyance direction). Ru. When the colorimeter 46 is configured with a scanner, the image is read while moving the scanner in a direction (paper conveyance direction) perpendicular to the direction in which the scanner is arranged. Then, the colorimeter 46 measures the color density of the image formed on the paper Sh for each area obtained by dividing the area where the image is read into a mesh shape. The colorimeter 46 outputs information on the measured color density to the inspection processing device 5.

Note that the colorimeter 46 may be configured with a single sensor, and the color density of the image formed on the paper Sh may be measured by moving the sensor two-dimensionally. Alternatively, the colorimeter 46 may be configured with a plurality of sensors arranged two-dimensionally (in a matrix), and the color density of all pixels on the paper may be read by one measurement using the plurality of sensors.

The image inspection apparatus 3 includes transport paths 42 and 43 connected to a transport path 41.
The conveyance path 42 is a path that branches off from the middle of the conveyance path 41, and discharges the paper Sh inspected by the inspection processing device 5 to a paper discharge tray 47 (an example of a paper discharge section). A sheet Sh (also referred to as "normal sheet") whose image is determined to be normal by the inspection processing device 5 is discharged to the sheet discharge tray 47 .

The conveyance path 43 is also a path that branches off from the middle of the conveyance path 41, and discharges the paper Sh inspected by the inspection processing device 5 to a paper discharge tray 48 (an example of a paper discharge section). A sheet Sh whose image is determined to be abnormal by the inspection processing device 5 (also referred to as “abnormal sheet”) is discharged to the sheet discharge tray 48 .

The switching unit 44 switches the conveyance direction of the paper Sh so that the paper Sh is conveyed to either of the conveyance paths 42 and 43. Note that if the image inspection apparatus 3 has only one paper ejection tray 47, normal sheets and abnormal sheets are mixed and ejected. In this case, the normal paper and the abnormal paper are ejected, for example, with a slight shift in the direction perpendicular to the ejecting direction.

The paper Sh conveyed to the image inspection device 3 is a printed matter with images formed on both sides or one side. The image inspection device 3 reads the images formed on both sides or one side of the paper Sh by the image forming device 2, and the inspection processing device 5 performs a predetermined inspection.

In this embodiment, since the image forming apparatus 2 is capable of forming images on both sides of the paper Sh, an example is given in which the inspection processing apparatus 5 inspects both sides of the paper Sh. However, the inspection processing device 5 may be configured to inspect only one side of the paper Sh transported from an image forming apparatus capable of forming an image on only one side of the paper Sh.

[Configuration of control system of image forming apparatus]
Next, a configuration example of the control system of the image forming apparatus 2 will be described with reference to FIG.
FIG. 3 is a block diagram showing a configuration example of a control system of the image forming apparatus 2. As shown in FIG.
The image forming apparatus 2 mainly includes a communication I/F section 51, a paper transport section 24, an image input section 11, an image forming section 30, a control section 50, a storage section 52, a fixing section 36, and an operation display section 13. Be prepared.

The communication I/F unit 51 is an interface that transmits and receives data to and from the PC 6, which is a terminal operated by an operator, via a network or a dedicated line. As the communication I/F unit 51, for example, a NIC (Network Interface Card) is used.

The paper conveyance section 24 drives the conveyance path 21 shown in FIG. 2, conveyance rollers (not shown) provided on the reversal conveyance path 22, and the reversal section 23 under the control of the control section 50.

The control unit 50 includes a CPU (Central Processing Unit) 501, a ROM (Read Only Memory) 502, a RAM (Random Access Memory) 503, and an input image processing unit 504.
The ROM 502 stores programs executed by the CPU 501 of the control unit 50 or data used when executing the programs. The CPU 501 controls each part of the image forming apparatus 2 by reading a program stored in the ROM 502.
In the RAM 503, variables and parameters generated during arithmetic processing by the CPU 501 are temporarily written.

The input image processing unit 504 performs predetermined image processing (for example, rasterization processing) on the input image included in the job input from the PC 6 via the communication I/F unit 51 to create print image data. The input image processing unit 504 also performs image processing on the image data acquired from the document read by the image input unit 11 with the ADF 12 or on the image data acquired from the outside, and creates image data for printing. This printing image data is sent to the image forming section 30 and the image inspection device 3. In the image inspection apparatus 3, the print image data is saved as an output target image 603b (see FIG. 4, which will be described later).

The control unit 50 controls the paper transport unit 24 to drive the transport rollers and transport the paper Sh on the transport path 21. Further, the control unit 50 outputs the print image data created by the input image processing unit 504 to the image forming unit 30. The control unit 50 also controls the image forming unit 30 to form an image on the paper Sh. The control unit 50 also controls the fixing unit 36 to fix the image on the paper Sh.

Further, the control unit 50 receives an operation signal from the operation display unit 13 and performs control according to the operation signal. Further, the control unit 50 outputs a display signal to the operation display unit 13, and the operation display unit 13 displays various setting screens for inputting various operation instructions and setting information, and an operation screen for displaying various processing results. Display on panel. The information displayed on the operation display section 13 also includes a streak detection result 631 (see FIG. 4 described later) output from the image inspection device 3.

The storage unit 52 stores parameters used when the CPU 501 of the control unit 50 executes a program, data obtained by executing the program, and the like. For example, the storage unit 52 stores information such as image forming conditions for each density level. Note that the storage unit 52 may store a program executed by the CPU 501.

[Configuration of control system of image inspection device]
Next, a configuration example of the control system of the image inspection apparatus 3 will be described with reference to FIG. 4.
FIG. 4 is a block diagram showing a configuration example of a control system of the image inspection apparatus 3. As shown in FIG.

The image inspection apparatus 3 includes a communication I/F section 61, a paper transport section 62, a reading section 45, and a colorimeter 46 as main components. Further, the inspection processing device 5 attached to the image inspection device 3 includes a control section 60 and a storage section 63. Furthermore, a storage device 4 is attached to the inspection processing device 5 .

The communication I/F section 61 is an interface that transmits and receives data to and from the image forming apparatus 2 via a network. As the communication I/F unit 61, for example, a NIC is used.
The paper conveyance section 62 drives a conveyance roller (not shown) provided on the conveyance path 41 shown in FIG. 2 under the control of the control section 60.

As described above, the reading unit 45 reads the images formed on the top and bottom surfaces of the paper Sh being conveyed through the conveyance path 41. In this embodiment, the image data of the paper Sh read by the reading units 45a and 45b is referred to as a "read image". The image read by the reading unit 45 from the paper Sh on which the image is formed is stored in the RAM 603 of the control unit 60 as a read image 603a. Furthermore, the RIP-processed printing image data that the inspection processing device 5 receives from the image forming device 2 is stored in the RAM 603 as an output target image 603b.

In this embodiment, the reference image to be compared with the read image 603a is referred to as an "output target image." The output target image 603b is a bitmap-format image that has been subjected to rasterization processing (RIP processing) by the control unit 50 of the image forming apparatus 2 in advance. This output target image 603b becomes the source of the image that the image forming apparatus 2 forms on the paper Sh. Since the output target image 603b is used to form an image on the paper Sh by the image forming apparatus 2, the CMYK color mode is set. Note that an image determined in advance to be correct by the operator and read in advance by the reading unit 45 may be used as the output target image 603b. Further, the read image 603a and the output target image 603b may be stored in the storage unit 63 configured with a large-capacity HDD or the like. Furthermore, the color density information output from the colorimeter 46 to the image inspection apparatus 3 may be included in the read image 603a and the output target image 603b.

The control unit 60 includes a CPU 601 , a ROM 602 , a RAM 603 , an image conversion unit 611 , a position alignment unit 612 , a change amount calculation unit 613 , a defect feature amount extraction unit 614 , and a quality determination unit 615 .

The CPU 601 controls each part of the image inspection apparatus 3 by reading a program stored in the ROM 602. When the CPU 601 executes the program read from the ROM 602, the functions of the image conversion section 611, alignment section 612, change amount calculation section 613, defect feature amount extraction section 614, and quality judgment section 615 are realized.

The ROM 602 stores programs executed by the CPU 601 of the control unit 60 or data used when executing the programs. The ROM 602 is used as an example of a computer-readable non-transitory recording medium that stores a program executed by the CPU 601.

In the RAM 603, variables and parameters generated during arithmetic processing by the CPU 601 are temporarily written. As described above, the read image 603a, the output target image 603b, the difference images 603c1 and 603c2, the classification results 603d, the threshold image 603e, and the parameters 603f are also stored in the RAM 603.

The parameters 603f include various values set by the control unit 60 or the operator. The parameter 603f includes, for example, a defect detection threshold for detecting streaks from the streak feature amount described later. The image conversion unit 611, alignment unit 612, change amount calculation unit 613, defect feature amount extraction unit 614, and quality determination unit 615 perform various processes based on various values read from the parameter 603f.

The image conversion unit 611 performs image conversion to match the color mode of the output target image 603b to the color mode of the read image 603a. Here, the color mode of the read image 603a is RGB. Therefore, the image conversion unit 611 converts the color mode of the output target image 603b from CMYK to RGB. In the following description, the output target image 603b will be described on the assumption that the color mode has been converted to RGB.

Note that the image conversion unit 611 may perform image conversion to match the color mode of the read image 603a to the color mode of the output target image 603b. Furthermore, if the color mode of the read image 603a is the same as the color mode of the output target image 603b, the image conversion process by the image conversion unit 611 may be omitted.

The alignment unit 612 aligns the printing positions of the output target image 603b and the read image 603a read from the sheet Sh on which the image is formed (referred to as "alignment"). For example, the alignment unit 612 aligns the print position of the output target image 603b, which serves as a reference for quality inspection of the image formed on the paper Sh, with the print position of the read image 603a. At this time, the alignment unit 612 aligns the read image 603a read from the RAM 603 to the position of the output target image 603b stored in the RAM 603 in advance.

The change amount calculation unit 613 generates a difference image 603c2 by calculating the difference between the output target image 603b aligned with the read image 603a by the alignment unit 612 and the output target image 603b shifted by the first number of pixels. Then, the difference image 603c2 is stored in the RAM 603. For example, the change amount calculation unit 613 uses the difference value between the pixel value of the pixel of interest 71 selected from a plurality of pixels included in the read image 603a and the pixel value of the comparison pixel 72 as the amount of change, and calculates the difference value at the position of the pixel of interest 71 as the change amount. Store. Then, the change amount calculation unit 613 performs similar difference processing on other pixels of the read image 603a to generate a difference image 603c1. At this time, the change amount calculation unit 613 calculates the difference between a shifted image (not shown) obtained by shifting the read image 603a by a predetermined number of pixels in the horizontal or vertical direction and the read image 603a before the shift, and generates a difference image. It is possible to generate 603c1. The shift represents the distance between pixels for determining the comparison pixel 72 with respect to the pixel of interest 71.

Further, the change amount calculation unit 613 generates a classification result 603d in which each pixel is classified into a plurality of types as a change amount based on the magnitude and sign of the difference value of each pixel included in the difference image 603c1. Here, the classification result 603d is expressed as a result of the change amount calculation unit 613 classifying (ternarizing) the difference value using a classification threshold for each of a plurality of pixels included in the difference image 603c1 (see FIG. bottom row). The classification threshold is a value set in the parameter 603f.

The change amount calculation unit 613 according to the present embodiment changes the classification threshold according to the alignment between the output target image 603b and the read image 603a (see FIG. 9, which will be described later). The changed classification threshold is set in the parameter 603f. However, the classification threshold may be set in advance according to the aligned output target image 603b and read image 603a.

Then, the change amount calculation unit 613 calculates a comparison pixel 72 which is separated from the pixel of interest 71 by the first number of pixels in the first direction with respect to the pixel of interest 71 selected from the plurality of pixels included in the read image 603a. The amount of change in pixel values is classified (ternarized). The amount of change in pixel value is expressed as a difference value between the pixel value of the pixel of interest 71 and the comparison pixel 72. Examples of the pixel of interest 71 and the comparison pixel 72 are shown in FIG. 5, which will be described later.

Further, before the multi-value conversion process, the change amount calculation unit 613 calculates a classification threshold that is varied in accordance with the amount of positional deviation representing the positional deviation of the output target image 603b with respect to the read image 603a. At this time, the change amount calculation unit 613 expands the range of the minimum value and maximum value of the classification threshold according to the amount of positional deviation that occurs in the main scanning direction.

Hereinafter, the first direction will be described as the main scanning direction and the second direction as the sub-scanning direction. However, if the direction of the line to be detected is the main scanning direction, the first direction may be the sub-scanning direction and the second direction may be the main scanning direction. That is, the first direction is either a horizontal direction parallel to the printing direction or a vertical direction perpendicular to the printing direction. Further, in this embodiment, the first number of pixels is "3".

In this embodiment, the process in which the change amount calculation unit 613 refers to the classification threshold and ternarizes the difference value of each pixel included in the difference image 603c1 for each pixel is referred to as "multi-value conversion." Depending on the classification threshold value, the change amount calculation unit 613 may convert the difference value of the difference image 603c1 into a multivalued form such as binarization, quaternary value, or the like. Further, the classification threshold is a value that is set in advance before the start of the image inspection, and a different value may be set depending on the resolution of the read image 603a, the type of image formed on the paper Sh, etc.

The above-mentioned classification threshold is generated as a threshold image 603e that the change amount calculation unit 613 refers to in order to generate the classification result 603d based on the difference image 603c2. The change amount calculation unit 613 changes the classification threshold according to the change in the pixel value of the read image 603a aligned by the alignment unit 612. The threshold image 603e is two types of images defined by a first classification threshold A and a second classification threshold B shown in FIGS. 7 to 9, which will be described later, and a classification threshold is stored for each pixel of the threshold image 603e. be.

Further, the change amount calculation unit 613 stores the difference value calculated by taking the difference between the pixel value of the pixel of interest 71 in the read image 603a and the pixel value of the comparison pixel 72 in the difference image 603c1 at the position of the pixel of interest 71. generate. At this time, the change amount calculation unit 613 calculates the difference between a shifted image (not shown) obtained by shifting the read image 603a by a predetermined number of pixels in the horizontal or vertical direction and the read image 603a before the shift, and generates a difference image. 603c1 is generated, and the difference image 603c1 is stored in the RAM 603.

Further, the change amount calculation unit 613 ternarizes the difference image 603c1 based on the generated threshold image 603e, that is, the first classification threshold A and the second classification threshold B (see FIGS. 7 to 9 described later). A classified result 603d is obtained.

Further, the change amount calculation unit 613 generates a classification result 603d in which each pixel is classified into a plurality of types as a change amount based on the magnitude and sign of the difference value of each pixel included in the difference image 603c1. Here, the classification result 603d is expressed as a result of the change amount calculation unit 613 classifying (ternarizing) the difference value using a classification threshold for each of a plurality of pixels included in the difference image 603c1 (see FIG. bottom row). The classification threshold is a value set in the parameter 603f.

The defect feature amount extraction unit 614 extracts the feature amount of a streak-like defect (“streak feature amount”) that occurs in the image formed on the paper Sh based on the amount of change classified based on a plurality of pixels in the sub-scanning direction. ) is extracted. For example, when the direction in which streaks occur is in the sub-scanning direction, the defect feature extracting unit 614 refers to the classification results 603d in the sub-scanning direction for each predetermined position in the main-scanning direction, and refers to the averaging result (ternary value). The line features are extracted from the averaged results). The ternary averaging result is the result obtained by the defect feature extracting unit 614 averaging the difference values that have been classified by the change amount calculation unit 613 using the classification threshold and multivalued, and is shown in the upper part of FIG. This is shown in a graph showing the ternary average value shown in the middle row. Details of the streak feature amount will be explained with reference to FIG. 6, which will be described later.

The quality judgment unit 615 compares the line feature amount with a preset defect detection threshold along the main scanning direction and determines the quality of the image formed on the paper Sh based on the presence or absence of a detectable line-like defect. Judge quality. At this time, the quality determining unit 615 determines that the read image 603a is normal if no streaks are detected from the streak feature amount. On the other hand, if the quality determining unit 615 detects streaks from the streak feature amount, it determines that the read image 603a is abnormal. The quality determining unit 615 then stores the streak detection result 631 including the page number of the page that is the source of the read image 603a in the storage unit 63.

The streak detection result 631 is not only stored in the storage unit 63 but also sent to the external storage device 4 connected to the image inspection apparatus 3. The storage device 4 may be, for example, a USB (Universal Serial Bus) memory, an SSD (Solid State Drive), an HDD (Hard Disk Drive), etc. connected to the image inspection device 3. By sending the streak detection result 631 to the storage device 4, the operator can display the streak detection result 631 stored in the storage device 4 and check the contents. Note that the streak detection result 631 may be transferred to and stored in a cloud server (not shown) or PC 6 connected via the communication I/F unit 61.

Further, the control unit 60 transmits the streak detection result 631 read from the storage unit 63 to the image forming apparatus 2 or the PC 6 via the communication I/F unit 61 as necessary. The image forming apparatus 2 can display the streak detection result 631 on the operation display section 13. Therefore, the operators of the image forming apparatus 2 and the image inspection apparatus 3 can check the contents of the streak detection result 631 from the operation display section 13. Further, the operator can also check the contents of the streak detection result 631 from the PC 6.

The control unit 60 selects a paper discharge tray (an example of a paper discharge destination) for the paper Sh conveyed through the conveyance path 41 according to the streak detection result 631. For example, the control unit 60 operates the switching unit 44 to discharge the normal paper transported to the transport path 42 to the paper ejection tray 47, and to discharge the abnormal paper transported to the transport path 43 to the paper ejection tray 48. Make paper.

Further, the control unit 60 performs a reprint process (referred to as “recovery process”) of the page corresponding to the read image 603a written as having a line in the line detection result 631 to the image forming apparatus 2 through the communication I/F unit 61. can be instructed. Note that the recovery process is performed automatically in the image inspection system 1 or manually by the operator after the operator has cleaned, replaced, etc. the rotating body that caused the streaks.

Next, a procedure for extracting a streak feature amount from a read image will be described with reference to FIGS. 5 and 6.
FIG. 5 is a diagram showing an example of a read image 603a that includes the streak 70 to be detected, and a classification result 603d.

An enlarged view (1) of the read image 603a in the upper part of FIG. 5 shows that a streak 70 to be detected occurs in the center of the read image 603a and in the sub-scanning direction. As shown in FIG. 1, which is data obtained by averaging pixel values in the sub-scanning direction, the variation period of density unevenness is large, so it may not be possible to reliably detect the streaks 70.

Therefore, the change amount calculation unit 613 selects the pixel of interest 71, selects a pixel near the pixel of interest 71 as the comparison pixel 72, and calculates the difference between the pixel of interest 71 and the comparison pixel 72. At this time, the change amount calculation unit 613 calculates the difference between the pixel value of the read image 603a and the comparison pixel 72 in the direction orthogonal to the line 70 to be detected. In this example, the difference between the pixel values of a pixel of interest 71 and a comparison pixel 72 in the main scanning direction is calculated. The closer the pixels to be compared, the less affected by density unevenness, but if the pixels to be compared are too close, the effect of streaks cannot be detected. For this reason, the change amount calculating unit 613 compares pixels that are separated by more than half the width of the stripe 70 to be detected. Then, the change amount calculation unit 613 generates a difference image 603c1 in which the difference value is stored at the position of the pixel of interest 71.

Next, the defect feature amount extraction unit 614 extracts the feature amount of the streak based on the difference value of each pixel included in the difference image 603c1 generated by the change amount calculation unit 613. Here, the defect feature amount extraction unit 614 calculates the difference value in the direction perpendicular to the streak (for example, the main scanning direction), and determines when the comparison pixel 72 is at the streak position and when the pixel of interest 71 is at the streak position. It is possible to obtain a large value with the opposite sign depending on when the position is reached (see graph (3) in FIG. 6, which will be described later).

However, although the value of the defect feature obtained from the difference value is large compared to a portion without streaks, the value itself is small. Therefore, the change amount calculation unit 613 classifies the difference value into three values depending on whether the difference value is larger than the first classification threshold value A or smaller than the second classification threshold value B, and obtains the classification result 603d. Note that the first classification threshold A is a larger value than the second classification threshold B. In the following description, when the first classification threshold A and the second classification threshold B are not distinguished, they are collectively referred to as "classification threshold".

The enlarged view (2) of the classification result 603d in the lower part of FIG. 5 shows an example of ternarizing the enlarged view (1) of the read image 603a in the upper part of FIG. The classification result 603d is obtained by the change amount calculation unit 613 converting the difference value of each pixel obtained from the read image 603a into three values. The classification result 603d is expressed by replacing each pixel with a value of "0", "128", or "255". Here, for ease of explanation, an example of the classification result 603d in which each pixel is colored is shown. In order to obtain such a classification result 603d, appropriate multi-value conversion is required. Therefore, in this embodiment, the classification threshold referred to in the multi-value processing is varied according to the area of the read image 603a.

FIG. 6 is a diagram showing how the streak feature amount is extracted from the classification result 603d.
Graph (1) in the upper part of FIG. 6 shows an example of the ternary average value. The defect feature extraction unit 614 calculates a ternary average value obtained by averaging the classification result 603d in the direction of the line to be detected. In this example, it is assumed that the stripe direction that the operator wants to detect is the sub-scanning direction. The ternary average value is expressed as a graph with a peak at the main scanning position "15" and a valley at the main scanning position "18".

Graph (2) in the middle of FIG. 6 also shows an example of the ternary average value. However, the ternary average value shown in graph (2) is at a position shifted to the right by three pixels (the number of pixels from target pixel 71 to comparison pixel 72) compared to graph (1), that is, in FIG. It represents the ternarized average value in a state where the pixel of interest 71 shown has been shifted to the position of the comparison pixel 72.

Graph (3) in the lower part of FIG. 6 shows the absolute value of the value obtained by subtracting graph (2) from graph (1) as the streak feature amount. Graph (3) shows that for values with opposite signs (for example, the main scanning position is "18"), a larger value is calculated than the values at other locations. Then, the quality determining unit 615 determines that a streak has occurred at this position if the streak feature amount calculated by taking the difference between the values of opposite signs is larger than the defect detection threshold C (for example, "150"). do.

By the way, not only flat image regions (referred to as "flat regions") but also uneven image regions (referred to as "non-flat regions") appear on printed matter. In the case of a flat area, the classification threshold may be changed depending on the density of the stripe to be detected (gradation difference in pixel values). Therefore, the change amount calculation unit 613 may extract only the flat area from the output target image 603b, and then the quality judgment unit 615 may detect streaks only in the extracted area. However, for example, streaks on a non-flat area where there is a gradation in which the amount of variation in pixel values is small are noticeable.

Then, when the change amount calculating unit 613 performs multi-value processing on the non-flat area where the amount of variation in pixel values is small using the classification threshold calculated based on the flat area, the quality determining unit 615 , there is a possibility that fluctuations having the same shape as the streaks in the output target image 603b will be mistakenly detected as streaks. Therefore, the change amount calculation unit 613 performs a process of dynamically changing the classification threshold using the output target image 603b.

<Classification threshold variation processing>
Here, the procedure for dynamically varying the classification threshold (referred to as "threshold variation processing") will be described with reference to FIGS. 7 to 9.

As a premise of this procedure, the output target image 603b whose color mode has been converted from CMYK to RGB by the image conversion unit 611 is aligned with the read image 603a by the alignment unit 612. Then, the change amount calculation unit 613 calculates a difference between the aligned output target image 603b and the pixel values of pixels in the read image 603a in a direction perpendicular to the streaks to be detected.

Here, the relationship between the difference between the flat region and the non-flat region and the classification threshold will be explained.
FIG. 7 is a graph showing an example of pixel values and difference values of pixels in a flat region and a non-flat region of the output target image 603b subjected to RIP processing, and classification threshold values. The horizontal axis of this graph represents the main scanning position, and the vertical axis represents three types of values (pixel value, difference value, and classification threshold). Further, the flat region and the non-flat region are defined by the difference value graph shown in the upper part of FIG. 7 . In the figure, the first classification threshold A is described as "threshold A", and the second classification threshold B is described as "threshold B".

The graph at the bottom of FIG. 7 represents fluctuations in pixel values of the output target image 603b that has been subjected to RIP processing. In addition, the graph on the upper side of FIG. 7 is the difference obtained by subtracting the pixel value obtained by shifting the output target image 603b by three pixels in the horizontal direction from the pixel value of the output target image 603b in the lower graph of FIG. Represents fluctuations in value.

The pixel values of the output target image 603b are represented by a graph of a polygonal line L1. The graph of the polygonal line L1 shows that the main scanning position from "1" to "7" is a flat region, so that both the pixel value and the difference value do not change. On the other hand, since the main scanning position from "7" to "33" is a non-flat region, the pixel value and the difference value change. For example, the pixel value in a non-flat area gradually increases from main scanning position "11" to "21" and maintains a constant value, then gradually decreases from "23" to "33" and returns to the original value. Return to “128”.

For example, the difference value obtained by subtracting the pixel value obtained by shifting the output target image 603b by three pixels in the horizontal direction from the pixel value of the output target image 603b is represented by a graph of a polygonal line L10. As shown in the graph of the line L10, the difference value in the non-flat area gradually decreases from main scanning position "7" to "9", takes a constant negative value from "9" to "17", and becomes " It gradually increases from 17" to 23". Then, it takes a constant positive value from the main scanning position "23" to "30", gradually decreases from "30" to "33", and returns to the original value "0".

Here, the value obtained by adding a predetermined value (for example, "8") to the difference value is called the first classification threshold A, and the value obtained by subtracting the predetermined value (for example, "8") to the difference value is called the first classification threshold A. , is called the second classification threshold B. The first classification threshold A is represented by a graph of a line L11, and the second classification threshold B is represented by a graph of a line L12. The classification threshold is stored in parameter 603f. The classification threshold is referred to by the change amount calculation unit 613 in order to ternarize the pixel specified at the main scanning position of the read image 603a.

As described above, the change amount calculation unit 613 determines whether the difference value shown in the graph of the polygonal line L10 is greater than the sum of the first classification threshold A, or the difference value is subtracted by the second classification threshold B. A classification result 603d is obtained in which the difference value is classified into three (ternarized) depending on whether the difference value is smaller than the calculated value or whether the difference value is greater than or equal to the second classification threshold B and less than or equal to the first classification threshold A. For this reason, the inventor considered that it is possible to detect streaks even in areas other than flat areas (non-flat areas) without false detection.

However, if a misalignment occurs in the alignment, a misalignment occurs between the positions of the threshold values A and B, which dynamically change in a non-flat area, and the position of the pixel to which they are originally intended. As a result, it has been found that erroneous detection of streaks occurs when the difference value exceeds or falls below the classification threshold for non-flat areas.

FIG. 8 is a diagram showing an example of a change in a graph representing a difference value when a misalignment occurs.
Due to a misalignment of the read image 603a with respect to the output target image 603b, the polygonal line L20 representing the change in the difference value is shifted to the left with respect to the polygonal line L10. As a result, a part of the polygonal line L20 comes into contact with the polygonal line L11 representing a change in the first classification threshold A at the main scanning position "17", and the difference value becomes larger than the first classification threshold A. Therefore, erroneous ternarization is performed at the main scanning position "17". As a result, there is a possibility that the presence of streaks may be detected even though there are no streaks.

By the way, considering the calculation cost involved in alignment processing, it is realistic to select a method that corrects the deviation in a somewhat global manner (enlargement, reduction, tilt correction, etc.), so a certain degree of local deviation is allowed. You may do so. Therefore, it is necessary to set the classification threshold in consideration of the positional deviation. A specific method is to increase the number of pixels covered by the classification threshold by the number of pixels where positional deviation may occur.

FIG. 9 is a diagram showing an example in which the classification threshold is varied.
The change amount calculation unit 613 expands the range of the classification threshold value, taking into consideration the occurrence of a shift in alignment. For example, the change amount calculation unit 613 expands the range of the classification threshold by the amount by which the maximum or minimum value of the difference values shown in the polygonal line L20 is shifted from the original polygonal line L10. The figure shows how the range of the maximum value of the first classification threshold A is expanded and the range of the minimum value of the second classification threshold B is expanded.

Since the range of classification thresholds has been expanded, the boundary of the shaded area 80 is treated as a new classification threshold. Since the range of the classification threshold has been expanded in this way, even if the read image 603a deviates from its original position, the difference value shown by the polygonal line L20 calculated from the read image 603a will not exceed or fall below the classification threshold. The ternarization will be performed correctly without any error.

Next, an example of processing performed by the inspection processing device 5 will be described with reference to FIG. 10.
FIG. 10 is a flowchart illustrating an example of processing performed by the inspection processing device 5 according to one embodiment.

First, the image conversion unit 611 converts the color mode of the output target image 603b read from the RAM 603 from CMYK to RGB (S1). Through this process, the image conversion unit 611 adjusts the color mode of the output target image 603b (RIP image) received by the image inspection apparatus 3 from the image forming apparatus 2 to the color mode of the read image 603a.

Next, the alignment unit 612 performs alignment processing to align the RGB-converted output target image 603b with the read image 603a (S2). Next, the change amount calculation unit 613 shifts the output target image 603b by the first number of pixels (S3). In this embodiment, the output target image 603b is shifted by three pixels in the horizontal direction.

Next, the change amount calculation unit 613 generates a difference image 603c2 (for example, an image similar to FIG. 6) based on the shifted image obtained in step S3 and the output target image 603b that has not been processed in step S3. (S4).

Next, the change amount calculation unit 613 sets a value obtained by adding a predetermined value to each pixel value of each pixel included in the difference image 603c2 as a first classification threshold A, and a value obtained by subtracting the predetermined value as a second classification threshold B. A threshold image 603e is generated (S5). At this time, as shown in FIGS. 8 and 9, the change amount calculation unit 613 also performs processing to expand the range of the maximum and minimum values of the classification threshold, taking into account the misalignment of the read image 603a with respect to the output target image 603b. conduct. The generated threshold image 603e is then temporarily stored in the RAM 603.

In parallel with the processing in steps S2 to S5, the change amount calculation unit 613 performs the processing in steps S11 and S12. The change amount calculation unit 613 shifts the read image 603a (for example, FIG. 5) read from the RAM 603 and input by a first number of pixels (for example, 3 pixels) (S11). Then, the change amount calculation unit 613 generates a difference image 603c1 based on the shifted image obtained in step S11 and the read image 603a that has not been processed in step S11 (S12).

After the processing in steps S5 and S12, the change amount calculation unit 613 performs ternarization processing on the difference image 603c1 based on the first classification threshold A and the second classification threshold B read out from the parameter 603f, and converts each pixel into A classification result 603d (for example, FIG. 5) including ternary values is generated (S13).

After steps S5 and S13, the defect feature extraction unit 614 extracts a streak feature (for example, graph (3) in FIG. 6) based on the classification result 603d (S14). The quality determining unit 615 then compares the streak feature amount with the defect detection threshold read out from the parameter 603f, detects a streak (S15), and determines the quality of the read image 603a. The quality determination unit 615 writes the streak detection result 631 into the storage unit 63. After that, the inspection processing device 5 ends this process.

The inspection processing device 5 according to the embodiment described above generates a threshold image 603e defined by a classification threshold for the difference value included in the difference image 603c2 between the read image 603a and the output target image 603b. At this time, the change amount calculation unit 613 expands the range of the classification threshold value, taking into consideration the occurrence of a misalignment between the read image 603a and the output target image 603b. In addition, the inspection processing device 5 obtains a difference image 603c1 by calculating the difference between a shifted image obtained by shifting the read image 603a by several pixels and the read image 603a. Therefore, in the process of ternarizing the difference values of the difference image 603c1 by the change amount calculation unit 613, it is possible to prevent the difference values of the non-flat area from being erroneously ternarized. Then, based on the feature extracted by the defect feature extraction unit 614, the quality judgment unit 615 can accurately detect thin streaks from non-flat areas that may be noticeable when an operator visually inspects the printed matter. It becomes like this.

Furthermore, regarding the streaks occurring in the non-flat area of the read image 603a, the pixel values are converted into three values by the ternarization process and the streak feature amount is extracted, so that the detection accuracy of the streaks can be improved.

Note that for wide stripes, the influence of the stripes (changes in pixel values) is gentle. Therefore, if the position of a pixel extracted as a comparison pixel is too close to the pixel of interest, the difference between the pixel and the comparison pixel becomes small, making it impossible to detect a streak. On the other hand, if the comparison pixel is too far away from the pixel of interest, streaks occurring in a narrow flat area cannot be detected.

Therefore, the first number of pixels that the change amount calculation unit 613 calculates to obtain the difference image 603c1 may be a plurality of different values (for example, 3 pixels, 5 pixels, 7 pixels, and 15 pixels). Then, the change amount calculation unit 613 may generate a plurality of difference images 603c1 in which difference values calculated for each of a plurality of different values are stored at the position of the pixel of interest. By setting a plurality of shift numbers of comparison pixels to be shifted with respect to the pixel of interest in the parameter 603f, the change amount calculation unit 613 calculates the difference between one pixel of interest and comparison pixels shifted by different shift numbers. , the presence or absence of streaks may be analyzed in parallel. Through such processing, the defect feature extracting unit 614 may extract the streak feature from each of the plurality of difference images 603c1, and the quality determining unit 615 may detect the streak from the extracted streak feature. Thereby, it is possible to detect the streaks appearing in the read image 603a, regardless of the thickness of the streaks.

[Modification of one embodiment]
The positional deviation between the read image 603a and the output target image 603b shown in the embodiment described above can occur not only in the main scanning direction but also in any direction. Therefore, it is necessary to expand the range of classification thresholds not only in a direction perpendicular to the streaks to be detected but also in parallel or diagonal directions. Therefore, the change amount calculation unit 613 according to the present modification expands the detection exclusion region in which the quality determination unit 615 does not perform the process of detecting streaks by the amount of positional deviation allowed by the alignment unit 612. Specifically, the change amount calculation unit 613 expands the range of the classification threshold two-dimensionally.
FIG. 11 is a diagram showing how the range of classification thresholds is expanded two-dimensionally.

The left side of FIG. 11 shows that the read image 603a includes only one character (“a”). The right side of FIG. 11 shows an enlarged portion of the characters. Conventionally, the classification threshold range is not expanded, so the classification threshold range 91 before expansion coincides with the edge of the character. However, the change amount calculation unit 613 according to this modification expands the range of the classification threshold two-dimensionally. Therefore, the change amount calculation unit 613 expands the range of the minimum value and maximum value of the classification threshold according to the amount of positional deviation that occurs in the main scanning direction and the sub-scanning direction.

In the figure, a pixel of interest 92 is represented by a star. The pixel of interest 92 is located two pixels outside the edge of the character. Then, the change amount calculation unit 613 sets a mask 93 (an example of a region) to be a range obtained by adding two pixels in the upper, lower, right, and left directions around each pixel of interest 92 as the center. The size of the mask 93 is determined by the amount of positional deviation that may occur in the read image 603a (for example, the specifications and characteristics of the image forming apparatus 2), and the size of the mask 93 is determined by the amount of positional deviation that may occur in the read image 603a. A predetermined length is set in the direction and the sub-scanning direction. In FIG. 11, the size of the mask 93 is set to a length of five pixels in each of the main scanning direction and the sub-scanning direction. However, the lengths of the mask 93 in the main scanning direction and the sub-scanning direction may be different.

Then, the change amount calculation unit 613 performs filter processing to obtain the maximum value of the pixel values within the mask 93. Then, multilevel conversion is performed based on the maximum value taken within the mask 93. In other words, the classification threshold range is extended to the mask 93 that moves together with the pixel of interest 92 within a range in which the pixel of interest 92 can move along the inside of the threshold range 94 indicated by the broken line. In this way, the change amount calculation unit 613 sets the maximum value of the change amount included in the mask 93 as the maximum value of the classification threshold used inside the mask 93. However, filter processing may be combined in which the minimum value of the amount of change included in the mask 93 is set as the minimum value of the classification threshold used inside the mask 93.

In this way, the change amount calculation unit 613 expands the range of the classification threshold two-dimensionally. With this enlargement process, even if the positional deviation between the read image 603a and the output target image 603b occurs not only in a direction perpendicular to the stripes to be detected but also in a direction parallel to the stripes or in a diagonal direction, the change amount calculation unit 613 can ternarize the difference value of the difference image 603c1. Therefore, the quality determining unit 615 can reliably detect streaks.

[Other variations]
Further, the change amount calculation unit 613 can generate a detection exclusion area in which no streaky defects are detected from the output target image 603b. In this case, the quality determination unit 615 does not perform the process of detecting the streaky defect in the detection exclusion area.

So far, we have described an example of dynamically changing the classification threshold for areas with small variations (e.g., gradation areas), but images with clear edges with large gradation variations (e.g., edges written on a thin background) Edges of black characters, etc.) also exist. In the vicinity of such a region, when the change amount calculation unit 613 performs difference calculation, it calculates a large difference value, so that the quality judgment unit 615 cannot detect streaks. Therefore, in consideration of the risk of erroneously detecting streaks, the change amount calculation unit 613 sets an edge region generated from the output target image 603b, in which a clear edge with a large amount of gradation variation exists, as a detection exclusion region. I can do it.

Further, if the cause of the streaks to be detected is dirt on the charging electrode or uneven coating of lubricant on the photoreceptor drum, the streaks will occur only in the image area where toner adheres, and will not occur in the white area of the paper. In addition, noise is likely to occur in the read image 603a in the white area of the paper, and there is also a possibility that show-through may occur in which a part of the image formed on the back side can be seen through. Therefore, the change amount calculation unit 613 calculates a classification threshold value that is generated from the output target image 603b and is matched to the paper white area where no image is formed. By using the calculated classification threshold, the change amount calculation unit 613 can accurately perform multi-value conversion.

However, if noise is likely to occur in the paper white area and show-through is likely to occur, the change amount calculation unit 613 may use the paper white area where no image is formed, which is generated from the output target image 603b, as the detection exclusion area. . Specifically, the change amount calculation unit 613 detects a paper white area on which no coloring material is applied from the output target image 603b, and treats that area as an exclusion area for streak detection. By setting the paper white area as a detection excluded area in this way, it is possible to avoid erroneous detection of streaks by the quality determining unit 615.

Note that streaks may occur in the paper white area due to poor cleaning during secondary transfer. In order for the quality determination unit 615 to detect such streaks, it is necessary to not detect noise in the paper white area. Streaks occur in the paper white area when toner is placed on the paper white area in a streak-like manner, and in this case, a large difference value is calculated. Therefore, the change amount calculation unit 613 may set the classification threshold of the paper white area detected from the read image 603a to be detected only when the difference value is large. Furthermore, the edge area and the paper white area are also affected by the misalignment that occurs during alignment. Therefore, it is desirable to expand the range of the detection exclusion area also with respect to the edge area and the paper white area, taking into account the positional deviation.

In the embodiment described above, the image inspection apparatus 3 and the inspection processing apparatus 5 are combined. It's okay. Further, the image forming apparatus 2 may have the function of the inspection processing apparatus 5, and the image forming apparatus 2 may perform image inspection by itself. Further, by configuring an image forming system by providing a server having the function of the inspection processing device 5, the server may accumulate the read image 603a and the output target image 603b read from the paper Sh by the image inspection device 3. Then, the server may communicate with the image inspection apparatus 3 to detect streaks in the read image 603a received from the image inspection apparatus 3, and transmit the streak detection results to the image inspection apparatus 3 and the PC 6.

Note that the present invention is not limited to the embodiments described above, and it goes without saying that various other applications and modifications can be made without departing from the gist of the present invention as set forth in the claims.
For example, the embodiments described above describe the configurations of devices and systems in detail and specifically in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to having all the configurations described. Furthermore, it is possible to replace a part of the configuration of the embodiment described here with the configuration of other embodiments, and it is also possible to add the configuration of another embodiment to the configuration of a certain embodiment. It is possible. Furthermore, it is also possible to add, delete, or replace some of the configurations of each embodiment with other configurations.
Further, the control lines and information lines are shown to be necessary for explanation purposes, and not all control lines and information lines are necessarily shown in the product. In reality, almost all components may be considered to be interconnected.

DESCRIPTION OF SYMBOLS 1... Image inspection system, 2... Image forming device, 3... Image inspection device, 5... Inspection processing device, 30... Image forming section, 45... Reading section, 60... Control section, 603a... Read image, 603b... Output target image , 603c1, 603c2...difference image, 603d...classification result, 603e...threshold image, 603f...parameter, 611...image conversion unit, 612...alignment unit, 613...change amount calculation unit, 614...defect feature amount extraction unit, 615 ...Quality judgment unit, 631...Streak detection result

Claims (7)

a positioning unit that aligns an output target image that is a source of an image formed on a recording material by the image forming apparatus and a read image read from the recording material on which the image is formed;
Based on a classification threshold for classifying a difference image generated by taking a difference between a shifted image obtained by shifting the read image by a predetermined number of pixels in the horizontal or vertical direction and the read image before shifting, a change amount calculation unit that classifies the amount of change in the pixel value of a comparison pixel that is separated by a first number of pixels in a first direction with the pixel of interest as a reference, with respect to the pixel value of a pixel of interest selected from the read image;
a feature amount of a streak-like defect occurring in the image formed on the recording material, based on the amount of change classified based on a plurality of pixels in a second direction intersecting the first direction; a feature extraction unit that extracts
Quality determination for detecting the streaky defect by comparing the feature amount with a preset defect detection threshold along the first direction, and determining the quality of the image formed on the recording material. An image inspection device comprising: The image inspection apparatus according to claim 1, wherein the change amount calculation unit calculates the classification threshold value that is generated from the output target image and is adjusted to a paper white area where the image is not formed. The change amount calculation unit generates a detection exclusion area in which the streaky defect is not detected from the output target image,
The image inspection apparatus according to claim 1 or 2, wherein the quality judgment unit does not perform the process of detecting the streaky defect in the detection exclusion area. The image inspection apparatus according to claim 3, wherein the change amount calculation unit sets an edge region generated from the output target image as the detection exclusion region. The image inspection apparatus according to claim 3 , wherein the change amount calculation unit sets a paper white area in which the image is not formed, which is generated from the output target image, as the detection exclusion area. The image inspection apparatus according to any one of claims 1 to 5, further comprising a reading section that reads the image from the recording material and generates the read image. An image forming apparatus that forms an image on a recording material, and an image inspection apparatus that inspects the image formed on the recording material,
The image inspection device includes:
a positioning unit that aligns an output target image that is the source of the image formed on the recording material by the image forming apparatus and a read image read from the recording material on which the image is formed;
Based on a classification threshold for classifying a difference image generated by taking a difference between a shifted image obtained by shifting the read image by a predetermined number of pixels in the horizontal or vertical direction and the read image before shifting, a change amount calculation unit that classifies the amount of change in the pixel value of a comparison pixel that is separated by a first number of pixels in a first direction with the pixel of interest as a reference, with respect to the pixel value of a pixel of interest selected from the read image;
a feature amount of a streak-like defect occurring in the image formed on the recording material, based on the amount of change classified based on a plurality of pixels in a second direction intersecting the first direction; a feature extraction unit that extracts
Quality determination for detecting the streaky defect by comparing the feature amount with a preset defect detection threshold along the first direction, and determining the quality of the image formed on the recording material. An image inspection system comprising:

Images