JP7115266B2 - IMAGE INSPECTION APPARATUS, IMAGE INSPECTION METHOD AND IMAGE INSPECTION PROGRAM - Google Patents

Description

The present invention relates to an image inspection apparatus, an image inspection method, and an image inspection program, and more particularly to an image inspection apparatus, an image inspection method, and an image inspection program for inspecting a read image.

An electrophotographic printed matter may have an abnormality that is not found in an image to be printed. For example, in electrophotography, spot-like abnormalities due to the so-called firefly phenomenon may occur during transfer, and these spot-like abnormalities appear as light undulations on a halftone image. The abnormality caused by the firefly phenomenon occurs when the developer is filled with a high packing density, the developer is compressed and solidified in the space of the container body, and the developer clumps adhere to the paper. . Therefore, it is known that the above-mentioned abnormality does not occur in the paper white portion where no image is formed.

Methods for optically inspecting such abnormalities are not limited to the field of printing, and there are many known methods. For example, Japanese Unexamined Patent Application Publication No. 2002-200001 discloses a method for optically inspecting defects in an object having a repeated pattern area as a method for inspecting the appearance of a semiconductor wafer, in which a change in gradation due to defects is removed from the captured image of the repeated pattern area. a process of generating a reference image by using the reference image, a process of obtaining an image in which only the amount of steep grayscale change is extracted by comparing the reference image and the captured image, and a process of binarizing the brightness value of the extracted image to detect the defective part. A configuration for performing processing for determining the presence or absence of is disclosed.

Further, Patent Document 2 below discloses an inspection area creation method for extracting, as an inspection area, only a specific area in which a predetermined process has been performed on an inspection object, and includes a step of capturing an image of the inspection object before processing; a step of extracting an inspection candidate area having a specific brightness from the captured image; a step of capturing an image of the processed inspection object; a step of measuring the brightness of the inspection candidate area from the captured image; and extracting, as an inspection area, an area having different brightness before and after processing from among the inspection candidate areas.

Japanese Patent Application Laid-Open No. 2001-209798 JP-A-11-34448

As mentioned above, the firefly phenomenon occurs on halftone images, so when inspecting the entire surface of a printed matter, it is possible that an abnormality caused by the firefly phenomenon will be falsely detected due to the influence of the noise component in areas other than the halftone density. have a nature. To address this problem, Patent Document 2 discloses that an inspection candidate area having a specific luminance is extracted from an image of an inspection object before processing, and the luminance of the inspection candidate area is measured from an image of the inspection object after processing. Then, the brightness of the inspection candidate area before and after the process is compared, and the area with different brightness before and after the process is extracted as the inspection area from the inspection candidate area. Since the inspection area is not extracted (that is, the inspection area is extracted from the captured image of the inspection object), the process of extracting the inspection area becomes complicated. In addition, since this method extracts regions with different luminances as inspection regions, unnecessary portions may also be inspected.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and its main object is to provide an image inspection apparatus, an image inspection method, and an image inspection program capable of efficiently detecting specific abnormalities from read images. to do.

One aspect of the present invention includes an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, and an inspection area that creates an inspection area using the original image data. An image inspection apparatus comprising: a creation unit; and a read image analysis unit that analyzes the read image, detects a location where a specific abnormality occurs, and outputs a detection result. Detecting the location where the specific abnormality occurs in the area corresponding to the inspection area in the image , the inspection area creating unit removes the portion with a density of 0% in the original image. The inspection area is defined as the inspection area, and an area corresponding to a portion of the original image formed on the back surface of the reading surface, the density of which is equal to or higher than a predetermined value, is excluded from the inspection area .
According to another aspect of the present invention, an image reading unit reads an original image formed on a recording material based on the original image data to generate a read image, and an inspection area is created using the original image data. An image inspection apparatus comprising an inspection area creation unit and a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs a detection result,
The read image analysis unit detects a location where the specific abnormality occurs in an area corresponding to the inspection area in the read image, and the inspection area creation unit detects an area in the original image. , an area excluding a portion with a density of 0% is defined as the inspection area, and an area corresponding to a portion having a size equal to or less than a predetermined value in the original image formed on the back side of the reading surface is excluded from the inspection area. It is characterized by
According to another aspect of the present invention, an image reading unit reads an original image formed on a recording material based on the original image data to generate a read image, and an inspection area is created using the original image data. An image inspection apparatus comprising: an inspection area creation unit; and a read image analysis unit that analyzes the read image to detect a location where a specific abnormality has occurred and outputs a detection result, wherein the read image analysis unit comprises: The read image analysis unit detects the location where the specific abnormality occurs in the area corresponding to the inspection area in the read image, and deleting from the detection results the areas detected from the area corresponding to the part whose density is equal to or greater than a predetermined value and/or the area corresponding to the part whose size is equal to or smaller than the predetermined value.
According to another aspect of the present invention, an image reading unit reads an original image formed on a recording material based on the original image data to generate a read image, and an inspection area is created using the original image data. An image inspection apparatus comprising: an inspection area creation unit; and a read image analysis unit that analyzes the read image to detect a location where a specific abnormality has occurred and outputs a detection result, wherein the read image analysis unit comprises: Detecting the location where the specific abnormality occurs in the area corresponding to the inspection area in the read image, the read image analysis unit detects an edge from the read image, and detects the vicinity of the edge. an exclusion processing unit that excludes an area from the inspection region; a filtering processing unit that performs a predetermined filtering process on the read image after the exclusion process to generate a first reference image; and the read image after the exclusion process. A comparison processing unit that compares the first reference image and generates a first comparison image, and binarizes the first comparison image using a predetermined threshold value to generate the specific abnormality. and an abnormal point detection unit that detects the point where the error occurs.

One aspect of the present invention is an image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, wherein the original image data and a read image analysis process of analyzing the read image to detect a location where a specific abnormality occurs and outputting the detection result, In the read image analysis process, the location where the specific abnormality occurs is detected in the area corresponding to the inspection area in the read image, and in the inspection area creation process, in the original image, A region other than a portion with a density of 0% is defined as the inspection region, and a region corresponding to a portion having a density greater than or equal to a predetermined value in the original image formed on the back side of the reading surface is excluded from the inspection region . characterized by
One aspect of the present invention is an image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, wherein the original image data and a read image analysis process of analyzing the read image to detect a location where a specific abnormality occurs and outputting the detection result, In the read image analysis process, the location where the specific abnormality occurs is detected in the area corresponding to the inspection area in the read image, and in the inspection area creation process, in the original image, A region excluding a portion with a density of 0% is defined as the inspection region, and a region corresponding to a portion having a size equal to or less than a predetermined value in the original image formed on the back side of the reading surface is excluded from the inspection region. characterized by
One aspect of the present invention is an image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, wherein the original image data and a read image analysis process of analyzing the read image to detect a location where a specific abnormality occurs and outputting the detection result, In the read image analysis process, the portion where the specific abnormality occurs is detected in the area corresponding to the inspection area in the read image. and/or deleting from the detection result the area detected from the area corresponding to the area having density equal to or greater than a predetermined value and/or the area corresponding to the area having size equal to or smaller than the predetermined value in the original image. and
One aspect of the present invention is an image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, wherein the original image data and a read image analysis process of analyzing the read image to detect a location where a specific abnormality occurs and outputting the detection result, In the read image analysis process, the location where the specific abnormality occurs is detected in the area corresponding to the inspection area in the read image, and in the read image analysis process, edges are detected from the read image. Then, an exclusion process for excluding an area near the edge from the inspection area, a filtering process for generating a first reference image by performing a predetermined filtering process on the read image after the exclusion process, and a filtering process for generating a first reference image after the exclusion process. comparing the read image with the first reference image to generate a first comparison image; and binarizing the first comparison image using a predetermined threshold to obtain the specific and an abnormal point detection process for detecting an abnormal point.

According to one aspect of the present invention, there is provided an image inspection program that operates in an image inspection apparatus including an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, and a control unit. wherein the control unit performs an inspection area creation process for creating an inspection area using the original image data, analyzes the read image, detects a location where a specific abnormality occurs, and outputs a detection result. and a read image analysis process is executed, wherein the read image analysis process detects the location where the specific abnormality occurs in the area corresponding to the inspection area in the read image, and detects the location of the inspection area. In the creation process, an area of the original image excluding a portion with a density of 0% is defined as the inspection area, and a portion of the original image formed on the back side of the reading surface with a density of a predetermined value or higher corresponds to the inspection area. It is characterized by excluding the area to be inspected from the inspection area .
According to one aspect of the present invention, there is provided an image inspection program that operates in an image inspection apparatus including an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, and a control unit. wherein the control unit performs an inspection area creation process for creating an inspection area using the original image data, analyzes the read image, detects a location where a specific abnormality occurs, and outputs a detection result. and a read image analysis process is executed, wherein the read image analysis process detects the location where the specific abnormality occurs in the area corresponding to the inspection area in the read image, and detects the location of the inspection area. In the creation process, an area of the original image excluding a portion having a density of 0% is defined as the inspection area, and corresponds to a portion of the original image formed on the back side of the reading surface whose size is equal to or less than a predetermined value. It is characterized by excluding the area to be inspected from the inspection area.
According to one aspect of the present invention, there is provided an image inspection program that operates in an image inspection apparatus including an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, and a control unit. wherein the control unit performs an inspection area creation process for creating an inspection area using the original image data, analyzes the read image, detects a location where a specific abnormality occurs, and outputs a detection result. a read image analysis process to be executed, wherein the read image analysis process detects a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image, and In the analysis process, of the original image formed on the back side of the reading surface, the above-mentioned portion detected from the area corresponding to the portion having density equal to or greater than a predetermined value and/or from the area corresponding to the portion having size equal to or less than a predetermined value. is deleted from the detection result.
According to one aspect of the present invention, there is provided an image inspection program that operates in an image inspection apparatus including an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image, and a control unit. In the control unit, an inspection area creation process for creating an inspection area using the original image data, analyzing the read image, detecting a location where a specific abnormality occurs, and outputting a detection result a read image analysis process to be executed, wherein the read image analysis process detects the location where the specific abnormality occurs in the area corresponding to the inspection area in the read image, and In the analysis process, an edge is detected from the read image, an exclusion process is performed to exclude an area near the edge from the inspection area, and a predetermined filter process is performed on the read image after the exclusion process to obtain a first reference image. comparison processing for generating a first comparison image by comparing the read image after exclusion processing with the first reference image; and the first comparison processing using a predetermined threshold value. and an abnormal point detection process of binarizing the comparison image and detecting the point where the specific abnormality occurs.

According to the image inspection apparatus, image inspection method, and image inspection program of the present invention, it is possible to efficiently detect a specific abnormality from a read image.

The reason for this is that an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image, an inspection area creating unit that creates an inspection area using the original image data, and a read image analysis unit that analyzes a read image, detects a location where a specific abnormality occurs, and outputs the detection result. This is because a location where a specific abnormality has occurred is detected in the region corresponding to .

1 is a schematic diagram showing a configuration example of an image inspection system according to a first embodiment of the present invention; FIG. FIG. 4 is a schematic diagram showing another configuration example of the image inspection system according to the first embodiment of the present invention; 1 is a block diagram showing the configuration of an image inspection apparatus according to a first embodiment of the present invention; FIG. FIG. 4 is a flow chart diagram showing the operation of the image inspection apparatus according to the first embodiment of the present invention; FIG. 4 is a flow chart showing the operation (abnormal part detection processing) of the image inspection apparatus according to the first embodiment of the present invention; 1 is a schematic diagram illustrating an image inspection method according to a first embodiment of the present invention; FIG. 1 is a schematic diagram illustrating an image inspection method according to a first embodiment of the present invention; FIG. It is a schematic diagram explaining the image inspection method based on the 2nd Example of this invention. It is a schematic diagram explaining the image inspection method based on the 3rd Example of this invention.

As shown in the background art, in electrophotography, spot-like abnormalities due to the firefly phenomenon may occur during transfer, and these spot-like abnormalities appear as faint undulations on halftone images. Here, when inspecting the entire surface of a printed matter, there is a possibility that an abnormality caused by a firefly phenomenon may be erroneously detected in a density portion other than halftones due to the influence of noise components. In response to this problem, Patent Document 2 proposes a method of extracting an inspection candidate area with a specific luminance from a captured image and extracting an inspection area from among them. Since the inspection area is not extracted, the process of extracting the inspection area becomes complicated. In addition, since this method extracts regions with different luminances as inspection regions, unnecessary portions may also be inspected.

Therefore, in one embodiment of the present invention, image data to be printed (referred to as original image data) is used so that specific abnormalities such as abnormalities caused by the firefly phenomenon can be efficiently detected from the read image. to create an inspection area, and detect a location where a specific abnormality occurs in the area corresponding to the inspection area in the read image.

Specifically, an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image, and an inspection area creation unit that creates an inspection area using the original image data. and a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs the detection result, wherein the read image analysis unit analyzes the read image for the inspection A location where a specific abnormality has occurred is detected in the area corresponding to the area.

At this time, the inspection area creating unit selects an area excluding a portion of the original image having a density of 0% as an inspection area, or selects a portion of the original image formed on the back side of the reading surface having a density of a predetermined value or more. Excluding the corresponding area from the inspection area, excluding the area corresponding to the part of the original image formed on the back side of the reading surface whose size is smaller than a predetermined value from the inspection area, and instructing the printing of the original image. If the print job specifies cutting, the area to be cut may be excluded from the inspection area. Further, the read image analysis unit detects from an area corresponding to a portion having a density equal to or greater than a predetermined value and/or an area corresponding to a portion having a size equal to or less than a predetermined value in the original image formed on the back side of the reading surface. The location may be deleted from the detection result.

By creating an inspection region using the original image data in this way, it is possible to suppress erroneous detection caused by the original image and efficiently detect a specific abnormality. In addition, by excluding unnecessary portions from the inspection area, the analysis time of the read image can be shortened, and specific abnormalities can be efficiently detected.

Further, the read image analysis unit detects an edge from the read image, an exclusion processing unit for excluding an area in the vicinity of the edge from the inspection area, and a predetermined filtering process for the read image after the exclusion processing to obtain a first reference image. a filter processing unit that generates an image; a comparison processing unit that compares the read image after exclusion processing with the first reference image to generate a first comparison image; and an abnormal location detection unit that binarizes the comparison image and detects a location where a specific abnormality has occurred. Further, the exclusion processing unit detects edges from the original image, excludes regions near the edges from the inspection region, and the filtering unit performs predetermined filtering on the original image after the exclusion processing. An image is generated, the comparison processing unit compares the original image after the exclusion process and the second reference image to generate a second comparison image, and the abnormal part detection unit is based on the second comparison image The first comparison image may be binarized using the threshold value set in step 1 to detect a location where a specific abnormality has occurred.

In this way, erroneous detection of content such as text and graphics included in the original image can be prevented by excluding the area near the edge with relatively high contrast from the inspection area. Further, by performing the blurring process as the filtering process applied to the inspection area, the abnormality caused by the firefly phenomenon can be included in the comparison image, and the specific abnormality can be reliably detected. In addition, by using the threshold obtained from the comparison image generated from the original image as the threshold, it is possible to reliably detect a specific abnormality.

In order to describe the above embodiment of the present invention in further detail, an image inspection apparatus, an image inspection method and an image inspection program according to the first embodiment of the present invention will be described with reference to FIGS. 1 to 7. do. 1 and 2 are schematic diagrams showing a configuration example of an image inspection system of this embodiment, and FIG. 3 is a block diagram showing a configuration of an image inspection apparatus of this embodiment. 4 and 5 are flowcharts showing the operation of the image inspection apparatus of this embodiment, and FIGS. 6 and 7 are schematic diagrams for explaining the image inspection method of this embodiment.

As shown in FIG. 1, the image inspection system 10 of the present embodiment performs RIP (Raster Image Processing) processing on a print job input from a computer device (not shown), and image data (original image) after the RIP processing. data), an image forming apparatus 12 having a printing unit for forming an image (referred to as an original image) on a recording material (paper) based on the original image data; It consists of an image inspection device 20 that reads the formed original image and inspects the finish of the printed matter. These are defined by standards such as Ethernet (registered trademark), token ring, FDDI (Fiber-Distributed Data Interface) Data communication is possible via a communication network 13 such as a LAN (Local Area Network) or a WAN (Wide Area Network).

The RIP unit of the controller 11 translates a print job described in PDL (Page Description Language) such as PCL (Printer Control Language) or PS (Post Script) to generate intermediate data, and color-codes the intermediate data. Color conversion is performed using the conversion table, and rendering is performed to generate image data for each page.

The printing section of the image forming apparatus 12 is composed of constituent elements necessary for image formation using an image forming process such as electrophotography, and prints an image based on image data on designated paper. Specifically, a photosensitive drum charged by a charging device is irradiated with light corresponding to an image from an exposure device to form an electrostatic latent image. An image is primarily transferred to a transfer belt, secondarily transferred from the transfer belt to a sheet, and a fixing device fixes the toner image on the sheet.

In FIG. 1, the image inspection system 10 is composed of the controller 11, the image forming apparatus 12, and the image inspection apparatus 20. However, when the image forming apparatus 12 is provided with the function of the image inspection apparatus 20, the configuration shown in FIG. As shown, the image inspection system 10 can also be configured with a controller 11 and an image forming device 12 . Further, when the image forming apparatus 12 is provided with the function of the controller 11 (the image forming apparatus 12 is provided with the RIP section), the image inspection system 10 is configured by combining the image forming apparatus 12 and the image inspection apparatus 20 (or only the image inspection apparatus 20). ) can also be configured. The image inspection apparatus 20 will be described below based on the configuration of FIG.

The image inspection apparatus 20 in the configuration of FIG. 1 includes, as shown in FIG. , a paper discharge unit 27, and the like.

The control unit 21 includes a CPU (Central Processing Unit) 21a and memories such as a ROM (Read Only Memory) 21b and a RAM (Random Access Memory) 21c, which are connected via a bus. The CPU 21a performs overall control of the image inspection apparatus 20 by reading programs from the ROM 21b and the storage unit 22, developing them in the RAM 21c, and executing them.

The storage unit 22 is composed of a HDD (Hard Disk Drive), an SSD (Solid State Drive), or the like, and stores a program for the CPU 21a to control each unit, original image data, and a read image obtained by reading an original image formed on a sheet of paper. Data, inspection area data created using original image data, threshold values calculated based on the original image, detection results of specific abnormalities (abnormalities caused by firefly phenomena in this embodiment), and the like are stored.

The network I/F unit 23 is composed of a NIC (Network Interface Card), a modem, etc., connects the image inspection apparatus 20 to the communication network 13, and enables reception of original image data from the controller 11. FIG.

The display operation unit 24 is configured by a touch panel or the like in which an operation unit such as a touch sensor having electrodes arranged in a grid pattern is formed on a display unit such as an LCD (Liquid Crystal Display) or an organic EL (Electro Luminescence) display. , various screens related to the operation of the image inspection apparatus 20 are displayed, and various operations related to the operation of the image inspection apparatus 20 are accepted. Note that the operation unit may include hard keys or the like, and the display unit and the operation unit may be separate devices.

The paper feeding unit 25 is composed of one or a plurality of paper feeding trays, and conveys paper on which an image (original image) has been formed by the image forming apparatus 12 to the image reading unit 26 .

The image reading unit 26 is a part that reads an image (original image) formed on a sheet of paper. An image is formed on the light-receiving surface of a sensor such as a sensor, and the image is read.

The paper discharge unit 27 is composed of one or a plurality of paper discharge trays, and discharges paper after image reading. In this embodiment, it is preferable to provide a plurality of paper discharge trays so that the paper on which a specific abnormality is detected by the abnormal part detection unit 33, which will be described later, can be discharged separately from the normal paper.

Further, the control section 21 functions as an inspection area creating section 28, a read image analyzing section 29, etc., as shown in FIG. 3(b).

The inspection area creating unit 28 creates an area (called an inspection area) for inspecting whether or not a specific abnormality has occurred using the original image data. For example, an area excluding a portion with a density of 0% in the original image (an area other than data with a density of 0% included in the original image data) may be set as an inspection area, or a print job instructing printing of the original image may be trimmed. is specified, the area to be trimmed is excluded from the inspection area.

The read image analysis unit 29 analyzes the read image acquired from the image reading unit 26, detects a location where a specific abnormality has occurred, and outputs the detection result. At that time, a location where a specific abnormality has occurred is detected in the area corresponding to the inspection area in the read image. The read image analysis unit 29 functions as an exclusion processing unit 30, a filter processing unit 31, a comparison processing unit 32, an abnormal location detection unit 33, and the like.

The exclusion processing unit 30 acquires a read image from the image reading unit 26, detects edges with relatively high contrast from the read image, and removes an area near the edge (an area surrounding a series of edges) from the inspection area. Exclude content such as text and graphics included in the original image so that it is not erroneously detected as an anomaly. Further, the exclusion processing unit 30 acquires an original image from the controller 11, the image forming apparatus 12, or the like, detects edges with relatively high contrast from the original image, and excludes areas near the edges from the inspection area. . In addition, if necessary, if the original image contains content having a frequency component equivalent to a specific abnormality (for example, an abnormality caused by a firefly phenomenon), the exclusion processing unit 30 removes the content from the abnormality detection target. exclude. Note that exclusion means deleting the area near the edge or content from the scanned image or the original image (in the case of an image with a uniform background, the area near the edge or content will be overwritten with the underlying image). , and setting so as not to detect an abnormal portion in an area near the edge or content without deleting the region near the edge or the content from the original image (or overwriting the content with the underlying image).

The filter processing unit 31 performs filter processing (blurring processing, for example, pixel value are averaged using the pixel values of the surrounding pixels) to generate a reference image (first reference image). Further, the filter processing unit 31 performs the same filter processing as that for the read image on the original image after the exclusion processing by the exclusion processing unit 30 to generate a reference image (second reference image).

The comparison processing unit 32 compares the read image after the exclusion processing by the exclusion processing unit 30 and the reference image (first reference image) to extract the difference, and creates a comparison image (first comparison image) composed of the difference. to generate In addition, the comparison processing unit 32 compares the original image after the exclusion processing by the exclusion processing unit 30 and the reference image (second reference image) to extract the difference, and creates a comparison image (second comparison image) made up of the difference. image).

The abnormal part detection unit 33 binarizes the first comparison image using a predetermined threshold value, detects a part where a specific abnormality (for example, an abnormality caused by a firefly phenomenon) occurs, and outputs the detection result. do. In this embodiment, in particular, a threshold value is calculated based on the second comparison image (comparison image generated from the original image), and the threshold value is used to binarize the first comparison image so that a specific abnormality occurs. Detects the location where it is detected and outputs the detection result. For example, the detection result is displayed on the display/operation unit 24, or the paper for which a specific abnormality is detected is output to a paper discharge tray different from the paper discharge tray for discharging normal paper.

The inspection region creation unit 28 and the read image analysis unit 29 (the exclusion processing unit 30, the filter processing unit 31, the comparison processing unit 32, the abnormal part detection unit 33) may be configured as hardware, and the control unit 21 may be The image inspection program is configured to function as the inspection area creation unit 28 and the read image analysis unit 29 (the exclusion processing unit 30, the filter processing unit 31, the comparison processing unit 32, and the abnormal part detection unit 33), and the image inspection program is executed in the CPU 21a. You can make it run.

Note that FIG. 3 is an example of the image inspection apparatus 20 of this embodiment, and the configuration thereof can be changed as appropriate. For example, in the case of the image inspection system 10 configured as shown in FIG. , the discharge unit 27 can be omitted.

A specific operation of the image inspection apparatus 20 of this embodiment will be described below with reference to FIGS. 4 to 7. FIG. The CPU 21a develops the image inspection program stored in the ROM 21b or the storage unit 22 in the RAM 21c and executes it, thereby executing the processing of each step shown in the flow charts of FIGS. In the following description, as shown in FIG. 6, the original image includes a uniform halftone image (represented by hatching dots in the figure), and one spot-like content is included in the original image. (In the case of FIG. 7, one spot-shaped content and one text content) are included, and a spot-shaped abnormality occurs at one location in the read image obtained by reading the original image.

As shown in FIG. 4, the control unit 21 (inspection area creation unit 28) creates an inspection area using the original image data (S101), and reflects the inspection area created from the original image data in the read image ( S102). For example, as shown in FIG. 6(b), a portion (here, a halftone image portion) other than white data (data with a density of 0%) is extracted from the original image data, and as shown in FIG. 6(c), Create an inspection area (see hatched area with oblique lines). The white data portion is a portion in which no toner image is formed, and is a region in which fireflies are not likely to occur in principle. When inspecting the entire read image for abnormalities caused by the firefly phenomenon, the firefly phenomenon usually occurs in light density areas. There is a possibility that a portion that is not an anomaly is also erroneously detected as an anomaly. Therefore, as shown in FIG. 6D, the inspection area created from the original image data is reflected in the read image, and the inspection target is limited to the portion where the toner image is formed. Note that here, an area excluding a portion of the original image having a density of 0% (an area other than the data having a density of 0% included in the original image data) is set as the inspection area, but the printing of the original image is instructed. If the print job specifies trimming, the trimming area may be excluded from the inspection area.

Next, the control unit 21 (read image analysis unit 29) analyzes the area corresponding to the inspection area in the read image, and detects the location where the specific abnormality (abnormality caused by the firefly phenomenon) has occurred (S103). , see FIG. 6(e)). At this time, if necessary, as shown in FIG. 6(f), a location where an abnormality other than the abnormality caused by the firefly phenomenon has occurred may be detected on the entire surface of the read image.

FIG. 5 shows an example of the abnormal part detection process of S103 of FIG. is detected, a region near the edge is specified, and the region near the specified edge is excluded from targets for detection of an abnormal portion (S201). For example, as shown in FIG. 7(b), a text region is identified by detecting characters printed in a color (for example, black) with high contrast to the ground color, and the text region is shown in FIG. 7(c). The specified area is deleted from the scanned image. Since the gradation fluctuates sharply in the vicinity of the edge, there is a risk of erroneous detection when detecting an abnormal portion. Therefore, erroneous detection can be prevented by detecting the edge portion and excluding the vicinity thereof from the detection target of the abnormal portion. Detection of this edge portion is generally known by a method using a differential filter represented by a Sobel filter. The position where the absolute value of the first derivative of the density change is maximum or the zero crossing of the second derivative of the density change is known. Positions can be detected as edges.

Next, the control unit 21 (filter processing unit 31) performs predetermined filter processing on the read image after the exclusion processing to generate a reference image (S202, see FIG. 7D). This filter is for the purpose of removing the frequency of the anomaly to be detected, and the strength and size of the filter depend on the anomaly to be detected. For example, the firefly phenomenon often occurs as a phenomenon with a diameter of about 1 to 3 mm, so by setting the size of the filter to about 5 mm, for example, it is possible to generate a reference image from which the influence of the firefly phenomenon is removed.

Next, the control unit 21 (comparison processing unit 32) compares the read image and the reference image to generate a comparison image (S203, see FIG. 7E). For example, a comparison image is generated by calculating the difference between pixel values at corresponding positions in two images. When this difference is calculated, a difference value is generated only at a location where there is a difference between the two images, that is, at a location where a spot-like abnormality originally occurred.

Here, the original image often contains some content in addition to halftones. For example, if the original image contains content that has the same frequency components as the anomaly that you want to detect, detecting an anomaly using only the read image will result in erroneous detection of an anomaly-free content. . Therefore, at locations where content exists in the original image, the threshold for detecting abnormal locations is raised to reduce detection sensitivity so that content locations are not erroneously detected.

Specifically, the control unit 21 (exclusion processing unit 30) acquires the original image from the controller 11, the image forming apparatus 12, or the like, detects high-contrast edges from the original image, and detects the vicinity of the edges. The area is specified, and the vicinity area of the specified edge is excluded from the detection target of the abnormal point (S204, see FIGS. 7(f) to (h)). Next, the control unit 21 (filter processing unit 31) performs the predetermined filter processing on the original image after the exclusion processing to generate a reference image (S205, see FIG. 7(i)). Next, the control unit 21 (comparison processing unit 32) compares the original image and the reference image to generate a comparison image (S206, see FIG. 7(j)). In this image, a difference value is generated only at the portion of the content that has the same frequency component as the spot-like abnormality that exists in the original image.

Next, the control unit 21 (abnormal part detection unit 33) sets a threshold for each position using the comparison image obtained from the original image (S207), and compares the comparison image generated from the read image with the set threshold. An abnormal point is detected by processing (binarization), and the detection result is output (S208, see FIG. 7(k)).

As described above, by creating an inspection region using original image data, it is possible to suppress erroneous detection due to the original image and efficiently detect specific abnormalities. Further, by excluding unnecessary portions such as portions with a density of 0% and areas to be trimmed from the inspection area, the analysis time of the read image can be shortened and specific abnormalities can be efficiently detected.

In addition, erroneous detection of content such as text and graphics included in the original image can be prevented by excluding areas near edges with relatively high contrast from detection targets for abnormal locations. Further, by performing the blurring process as the filtering process, it is possible to include the abnormality caused by the firefly phenomenon in the comparison image, and to reliably detect the specific abnormality. Further, by using a threshold obtained from a comparison image generated from the original image as the threshold, erroneous detection of content included in the original image can be prevented.

Next, an image inspection apparatus, image inspection method, and image inspection program according to a second embodiment of the present invention will be described with reference to FIG. FIG. 8 is a schematic diagram for explaining the image inspection method of this embodiment.

In the above-described first embodiment, the inspection area is the area excluding the 0% density portion of the original image (the area other than the 0% density data included in the original image data). When a printed matter printed on both sides of a recording material is read by a scanner or the like, a phenomenon occurs in which an image formed on the back side shows through to the front side. When this show-through occurs, a faint change in density similar to an abnormality caused by the firefly phenomenon appears on the surface.

Therefore, in this embodiment, a high-density portion (a portion having a density equal to or higher than a predetermined value) that may be affected by show-through is extracted from the original image data corresponding to the back surface of the inspection surface (the front surface that is the reading surface). to exclude from the inspection area.

In this case, the configuration of the image inspection apparatus 20 is the same as that of the first embodiment described above, but the inspection area creating unit 28 is configured so that the density of the original image formed on the inspection surface (reading surface) is 0%. After creating an area excluding the part (an area other than data with a density of 0% included in the original image data corresponding to the inspection surface) as an inspection area, the original image formed on the back side of the inspection surface has a predetermined density. A region corresponding to a portion having a density greater than or equal to the value (data having a density greater than or equal to a predetermined value included in the original image data corresponding to the back side of the inspection surface) (a region obtained by reversing the above portion) is excluded from the inspection region.

A specific operation of the image inspection apparatus 20 of this embodiment will be described below with reference to FIG. For example, as shown in FIG. 8B, the original image formed on the inspection surface includes a uniform halftone image (see hatching of dots), and as shown in FIG. The original image formed on the back surface of the inspection surface includes a portion with a density higher than a predetermined value (referred to as a high-density portion. Here, spot-like content), and as shown in FIG. Assume that a spot-like abnormality occurs at one location in the read image.

First, as shown in FIG. 8B, portions other than white data (data with a density of 0%) (halftone image portions in this case) are extracted from the original image data corresponding to the inspection surface, and the inspection area is determined. After that, as shown in FIG. 8(c), a high-density portion is extracted from the original image data corresponding to the back side of the inspection surface, and an area corresponding to the high-density portion (an area obtained by inverting the high-density portion) is obtained. By excluding it from the inspection area, an inspection area (see diagonal hatching) as shown in FIG. 8(d) is created. Next, as shown in FIG. 8E, the inspection area is reflected in the read image to limit the inspection target. Next, a location where a specific abnormality (abnormality caused by the firefly phenomenon) has occurred is detected from the area corresponding to the inspection area in the read image. Here, since the show-through portion is excluded from the inspection area, as shown in FIG.

In this way, by excluding the area corresponding to the high-density portion of the original image data corresponding to the back side from the inspection area created using the original image data corresponding to the inspection side (front side), the influence of show-through is reduced. Abnormalities caused by the firefly phenomenon can be detected with high precision in a short period of time.

In the above description, the case where the area corresponding to the high-density portion on the back side is excluded from the inspection area has been described. Alternatively, in addition to the high-density portion, an area corresponding to a portion whose size is equal to or smaller than the predetermined value (density-changing portion) may be excluded from the inspection area.

Next, an image inspection apparatus, image inspection method, and image inspection program according to a third embodiment of the present invention will be described with reference to FIG. FIG. 9 is a schematic diagram for explaining the image inspection method of this embodiment.

In the second embodiment described above, the original image data corresponding to the back side is used for a specific portion (a portion having a density equal to or greater than a predetermined value and/or a portion having a size equal to or smaller than a predetermined value) in which show-through may occur. Although the corresponding area is excluded from the inspection area, the inspection area is created using the original image data corresponding to the inspection surface. You may make it delete from a detection result. That is, when an abnormality caused by the firefly phenomenon is detected with the contents described in the first embodiment, it is difficult to determine whether an abnormality caused by the firefly phenomenon is actually detected or an abnormality caused by show-through is detected. Therefore, when an abnormality is detected from an area corresponding to a specific portion, it is determined that the effect is due to show-through rather than the firefly phenomenon, and is deleted from the detection result.

In this case, the configuration of the image inspection apparatus 20 is the same as that of the first embodiment described above, but the inspection area creating unit 28 creates a portion of the original image formed on the back surface where the density is equal to or higher than a predetermined value, and / Alternatively, when an abnormality is detected from a region corresponding to a portion whose size is equal to or less than a predetermined value, the location of the abnormality is deleted from the detection result.

For example, as shown in FIG. 9B, the original image formed on the inspection surface includes a uniform halftone image (see hatching of dots), and as shown in FIG. The original image formed on the back side of the inspection surface contains high-density spot-like contents, and as shown in FIG. occurs.

First, as shown in FIG. 9B, portions other than white data (data with a density of 0%) (here, halftone image portions) are extracted from the original image data corresponding to the inspection surface. An inspection area (see diagonal hatching) as shown in (d) is created. Next, as shown in FIG. 9E, the inspection area created from the original image data corresponding to the inspection surface is reflected in the read image, and the inspection target is limited to the portion where the toner image is formed. Next, as shown in FIG. 9(f), the area corresponding to the inspection area in the read image is analyzed to detect the location where a specific abnormality (abnormality caused by the firefly phenomenon) has occurred. Next, as shown in FIG. 9(g), if there is an abnormal portion detected from an area corresponding to a specific portion (here, a high-density portion) included in the original image formed on the back side, the abnormal portion Delete the occurrence location from the detection results.

In this way, in the original image formed on the back side of the inspection surface, when an abnormality is detected from an area corresponding to a portion having a density of a predetermined value or more and/or a portion having a size of a predetermined value or less, By determining that the abnormality is due to the show-through rather than the firefly phenomenon and deleting it from the detection result, the firefly phenomenon can be accurately detected without the influence of the show-through.

It should be noted that the present invention is not limited to the description of each of the above embodiments, and its configuration and control can be changed as appropriate without departing from the gist of the present invention.

For example, in the second embodiment, a portion that may be affected by show-through is excluded from the inspection area, and in the third embodiment, a portion detected from an area corresponding to the portion that may be affected by show-through is detected. is deleted from the detection results, but these can also be combined.

INDUSTRIAL APPLICABILITY The present invention can be applied to an image inspection apparatus for inspecting a read image, an image inspection method in the image inspection apparatus, an image inspection program operating in the image inspection apparatus, and a recording medium recording the image inspection program.

REFERENCE SIGNS LIST 10 image inspection system 11 controller 12 image forming apparatus 13 communication network 20 image inspection apparatus 21 control section 21a CPU
21b ROM
21c RAM
22 storage unit 23 network I/F unit 24 display operation unit 25 paper supply unit 26 image reading unit 27 paper discharge unit 28 inspection area creation unit 29 read image analysis unit 30 exclusion processing unit 31 filter processing unit 32 comparison processing unit 33 abnormal location Detection unit

Claims (15)

an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image;
an inspection area creation unit that creates an inspection area using the original image data;
An image inspection apparatus comprising a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs a detection result,
The read image analysis unit detects a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image,
The inspection area creating unit defines an area of the original image excluding a portion having a density of 0% as the inspection area, and determines an area having a density of a predetermined value or more in the original image formed on the back side of the reading surface. excluding regions corresponding to portions from the inspection region;
An image inspection apparatus characterized by: an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image;
an inspection area creation unit that creates an inspection area using the original image data;
An image inspection apparatus comprising a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs a detection result,
The read image analysis unit detects a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image,
The inspection area creating unit defines an area of the original image excluding a portion having a density of 0% as the inspection area, and the size of the original image formed on the back surface of the reading surface is equal to or less than a predetermined value. excluding the area corresponding to the portion of from the inspection area,
An image inspection apparatus characterized by: When cutting is specified in a print job that instructs printing of the original image, the inspection area creation unit excludes an area to be cut from the inspection area.
3. The image inspection apparatus according to claim 1 , wherein: an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image;
an inspection area creation unit that creates an inspection area using the original image data;
An image inspection apparatus comprising a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs a detection result,
The read image analysis unit detects a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image ,
The read image analysis unit detects from an area corresponding to a portion having a density equal to or greater than a predetermined value and/or an area corresponding to a portion having a size equal to or less than a predetermined value in the original image formed on the back side of the reading surface. deleting the location that has been detected from the detection result;
An image inspection apparatus characterized by: an image reading unit that reads an original image formed on a recording material based on the original image data and generates a read image;
an inspection area creation unit that creates an inspection area using the original image data;
An image inspection apparatus comprising a read image analysis unit that analyzes the read image, detects a location where a specific abnormality has occurred, and outputs a detection result,
The read image analysis unit detects a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image,
The read image analysis unit
an exclusion processing unit that detects an edge from the read image and excludes an area near the edge from the inspection area;
a filter processing unit that performs a predetermined filter process on the read image after the exclusion process to generate a first reference image;
a comparison processing unit that compares the read image after exclusion processing with the first reference image to generate a first comparison image;
an abnormal location detection unit that binarizes the first comparison image using a predetermined threshold to detect a location where the specific abnormality has occurred;
An image inspection apparatus characterized by: The exclusion processing unit detects an edge from the original image, excludes an area near the edge from the inspection area,
The filter processing unit performs the predetermined filter processing on the original image after exclusion processing to generate a second reference image,
The comparison processing unit compares the original image after exclusion processing with the second reference image to generate a second comparison image,
The abnormal location detection unit binarizes the first comparison image using a threshold set based on the second comparison image, and detects a location where the specific abnormality has occurred.
The image inspection apparatus according to claim 5 , characterized in that: The specific anomaly is an anomaly based on a firefly phenomenon,
The image inspection apparatus according to any one of claims 1 to 6, characterized in that: An image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image,
inspection area creation processing for creating an inspection area using the original image data;
Analyzing the read image, detecting a location where a specific abnormality has occurred, and executing a read image analysis process for outputting the detection result ,
In the read image analysis processing, detecting a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image ,
In the inspection area creation process, an area of the original image excluding a portion having a density of 0% is defined as the inspection area, and an area of the original image formed on the back side of the reading surface having a density equal to or higher than a predetermined value is used as the inspection area. excluding regions corresponding to portions from the inspection region;
An image inspection method characterized by: An image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image,
inspection area creation processing for creating an inspection area using the original image data;
Analyzing the read image, detecting a location where a specific abnormality has occurred, and executing a read image analysis process for outputting the detection result ,
In the read image analysis processing, detecting a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image ,
In the inspection area creation process, an area of the original image excluding a portion having a density of 0% is defined as the inspection area, and an area of the original image formed on the back side of the reading surface having a size equal to or less than a predetermined value is used as the inspection area. excluding regions corresponding to portions from the inspection region;
An image inspection method characterized by: In the inspection area creation process, if cutting is specified in a print job that instructs printing of the original image, the area to be cut is excluded from the inspection area.
10. The image inspection method according to claim 8 or 9 , characterized in that: An image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image,
inspection area creation processing for creating an inspection area using the original image data;
Analyzing the read image, detecting a location where a specific abnormality has occurred, and executing a read image analysis process for outputting the detection result ,
In the read image analysis processing, detecting a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image ,
In the read image analysis process, the original image formed on the back side of the reading surface is detected from an area corresponding to a portion having a density greater than or equal to a predetermined value and/or an area corresponding to a portion having a size less than or equal to a predetermined value. deleting the location that has been detected from the detection result;
The image inspection method according to any one of claims 8 to 10 , characterized in that: An image inspection method in an image inspection apparatus having an image reading unit that reads an original image formed on a recording material based on original image data and generates a read image,
inspection area creation processing for creating an inspection area using the original image data;
Analyzing the read image, detecting a location where a specific abnormality has occurred, and executing a read image analysis process for outputting the detection result ,
In the read image analysis processing, detecting a location where the specific abnormality occurs in a region corresponding to the inspection region in the read image ,
In the read image analysis process,
an exclusion process for detecting an edge from the read image and excluding an area near the edge from the inspection area ;
a filtering process for generating a first reference image by performing a predetermined filtering process on the read image after the exclusion process;
A comparison process of comparing the read image after the exclusion process and the first reference image to generate a first comparison image;
binarizing the first comparison image using a predetermined threshold to detect a location where the specific abnormality has occurred;
An image inspection method characterized by: In the exclusion process, an edge is detected from the original image, an area near the edge is excluded from the inspection area,
In the filtering process, the predetermined filtering process is performed on the original image after the exclusion process to generate a second reference image,
In the comparison processing, the original image after exclusion processing is compared with the second reference image to generate a second comparison image;
In the abnormal location detection process, the first comparison image is binarized using a threshold value set based on the second comparison image, and the location where the specific abnormality has occurred is detected.
The image inspection method according to claim 12 , characterized in that: The specific anomaly is an anomaly based on a firefly phenomenon,
The image inspection method according to any one of claims 8 to 13, characterized in that: An image inspection program for causing a computer to execute the processing included in the image inspection method according to any one of claims 8 to 14.

Images