IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND IMAGE PROCESSING PROGRAM

Abstract

To provide an image processing apparatus configured to exclude a false anomaly from detected anomalies to improve the accuracy of detecting anomalies, an image processing method, and an image processing program.SOLUTION: An anomaly detection unit 12 detects anomalies included in a target image. An anomaly exclusion processing unit 13 excludes a specific anomaly from the detected anomalies. When a detection area of a certain anomaly among the detected anomalies and a detection area of another anomaly overlap with each other and a type of the certain anomaly and a type of the other anomaly are different from each other, when luminance information of one of the certain anomaly and the other anomaly satisfies a specific condition, the anomaly exclusion processing unit 13 excludes the one of the certain anomaly and the other anomaly from the detected anomalies.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an image processing device, an image processing method, and an image processing program. [Background technology]

[0002] One image processing device detects abnormalities such as unintended streaks, dots, and unevenness that appear on print products output by image forming devices such as multifunction devices and printers based on images obtained by scanning the print products, and estimates the cause of each abnormality (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-223892 A Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, when trying to make it easier to detect anomalies, overdetection can occur, and images that are not abnormal can be detected as abnormal. Although the image processing device described above can detect anomalies, the detection results may include overdetected anomalies (false anomalies). In addition, subsequent processing such as estimating the cause of occurrence is performed on such false anomalies, which results in extra calculation costs.

[0005] The present invention has been made in consideration of the above problems, and aims to provide an image processing device, an image processing method, and an image processing program that can eliminate false anomalies from detected anomalies, thereby improving the accuracy of anomaly detection. [Means for solving the problem]

[0006] The image processing device according to the present invention includes an anomaly detection unit that detects anomalies included in a target image, and an anomaly exclusion processing unit that excludes a specific anomaly from the detected anomalies. When a detection area of ​​a certain anomaly and a detection area of ​​another anomaly overlap and the types of the certain anomaly and the other anomaly differ from each other, the anomaly exclusion processing unit excludes one of the certain anomaly and the other anomaly from the detected anomalies when luminance information of the certain anomaly and the other anomaly satisfy a predetermined condition. Furthermore, the anomaly exclusion processing unit (a1) derives a spatial luminance change distribution based on the luminance information, (a2) attempts to detect an area corresponding to the anomaly based on the luminance change distribution, and (a3) ​​excludes one of the one anomaly and the other anomaly from the detected anomalies if the detection result of the area satisfies the specified condition and (b) the type of the one anomaly and the type of the other anomaly are different from each other.

[0007] The image processing method according to the present invention comprises: A processing unit, an anomaly detection step for detecting an anomaly contained in the target image; A processing unit, and an anomaly excluding step of excluding a specific anomaly from the detected anomalies. In the anomaly excluding step, when a detection area of ​​a certain anomaly and a detection area of ​​another anomaly among the detected anomalies overlap and the type of the certain anomaly and the type of the other anomaly differ from each other, if luminance information of one of the certain anomaly and the other anomaly satisfies a predetermined condition, one of the certain anomaly and the other anomaly is excluded from the detected anomalies. Furthermore, in the anomaly exclusion step, (a1) a spatial luminance change distribution is derived based on the luminance information, (a2) an attempt is made to detect an area corresponding to the anomaly based on the luminance change distribution, and (a3) ​​if the detection result of the area satisfies the specified condition and (b) the type of the certain anomaly and the type of the other anomaly are different from each other, one of the certain anomaly and the other anomaly is excluded from the detected anomalies.

[0008] An image processing program according to the present invention causes a computer to function as the abnormality detection unit and the abnormality exclusion processing unit described above. Effect of the Invention

[0009] According to the present invention, an image processing device, an image processing method, and an image processing program are provided that can improve the accuracy of anomaly detection by eliminating false anomalies from detected anomalies.

[0010] The above and other objects, features and advantages of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing a configuration of an image processing device according to an embodiment of the present invention. [Diagram 2] FIG. 2 is a diagram showing an example of a filter used in the abnormality detection unit 12 in FIG. [Diagram 3] FIG. 3 is a diagram for explaining the correspondence between the filter output values ​​of a plurality of filters used in the abnormality detection unit 12 in FIG. 1 and the abnormality types. [Figure 4] FIG. 4 is a flowchart illustrating the operation of the image processing device shown in FIG. [Diagram 5] FIG. 5 is a flowchart illustrating the abnormality exclusion process (step S3) in FIG. [Figure 6] FIG. 6 is a diagram illustrating an example of the abnormality exclusion process (step S3) in FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0013] Fig. 1 is a block diagram showing the configuration of an image processing device according to an embodiment of the present invention. The image processing device shown in Fig. 1 is an information processing device such as a personal computer or a server, or an electronic device such as a digital camera or an image forming device (scanner, multifunction machine, etc.), and includes an arithmetic processing device 1, a storage device 2, a communication device 3, a display device 4, an input device 5, an internal device 6, etc.

[0014] The arithmetic processing device 1 includes a computer, and executes an image processing program on the computer to operate as various processing units. Specifically, the computer includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and operates as a specific processing unit by loading a program stored in the ROM or storage device 2 into the RAM and executing the program on the CPU. The arithmetic processing device 1 may also include an ASIC (Application Specific Integrated Circuit) that functions as a specific processing unit.

[0015] The storage device 2 is a non-volatile storage device such as a flash memory, and stores an image processing program and data necessary for the processing described below. The image processing program is stored in, for example, a non-transitory computer-readable recording medium, and is installed in the storage device 2 from the recording medium.

[0016] The communication device 3 is a device that performs data communication with an external device, such as a network interface, a peripheral device interface, etc. The display device 4 is a device that displays various information to the user, such as a display panel such as a liquid crystal display, etc. The input device 5 is a device that detects user operations, such as a keyboard, a touch panel, etc.

[0017] The internal device 6 is a device that executes a predetermined function of the image processing device. For example, if the image processing device is an image forming device, the internal device 6 is an image reading device that optically reads an original image from an original, a printing device that prints an image on a printing paper, or the like.

[0018] Here, the arithmetic processing device 1 operates as the target image acquisition unit 11, the abnormality detection unit 12, the abnormality exclusion processing unit 13, and the abnormality response processing unit 14, which are the processing units described above.

[0019] The target image acquisition unit 11 acquires a target image (image data) from the storage device 2, the communication device 3, the internal device 6, etc., and stores it in a RAM or the like.

[0020] The anomaly detection unit 12 detects anomalies contained in the acquired target image by using an existing method. In this embodiment, the anomaly detection unit 12 detects anomalies using, for example, a filter (second-order differential filter, Gabor filter, etc.) and generates feature information of the anomaly. In other words, anomalies are detected based on the feature amount (filter output) obtained by applying the filter to the input image.

[0021] The feature information includes the position and size of the abnormality (the position and size of the detection area described below), the type of the abnormality (streak, band, point, etc.), and the degree of abnormality corresponding to the output value of the filter when the abnormality is detected. For example, when the density difference between the surroundings of the abnormality and the abnormality is large, the degree of abnormality is large.

[0022] Fig. 2 is a diagram showing an example of a filter used in the abnormality detection unit 12 in Fig. 1. Fig. 3 is a diagram explaining the correspondence between the filter output values ​​of a plurality of filters used in the abnormality detection unit 12 in Fig. 1 and the abnormality types.

[0023] The anomaly detection unit 12 calculates the filter output value of each pixel P by moving a one-dimensional second-order differential filter as shown in Fig. 2 along directions A and B that intersect with each other, and classifies the shape pattern of the anomaly of each pixel P into a line or a point based on the filter output value of the pixel P in the A direction and the filter output value of the pixel P in the B direction, as shown in Fig. 3, for example, and identifies feature information such as the type of anomaly based on the shape pattern. For example, when a shape pattern (a pair of approximately parallel lines) of an edge portion of a line or band is detected by a one-dimensional second-order differential filter as shown in Fig. 2, the type of anomaly is identified as a line or band.

[0024] Anomaly exclusion processor 13 excludes a specific anomaly from the detected anomalies. Specifically, when a detection region of one anomaly among the detected anomalies overlaps with a detection region of another anomaly, and the type of the one anomaly and the type of the other anomaly are different from each other, if the luminance information of one of the one anomaly and the other anomaly satisfies a predetermined condition, anomaly exclusion processor 13 excludes one of the one anomaly and the other anomaly from the detected anomalies.

[0025] The detection area is a rectangular area that includes an abnormality, and is specified by the abnormality detection unit 12.

[0026] In this embodiment, one of the certain anomaly and the other anomaly is a point anomaly, and the other of the certain anomaly and the other anomaly is a muscle anomaly (or band anomaly). That is, among the detected anomalies, the anomaly exclusion process is performed on the point anomaly and the muscle anomaly (band anomaly) that overlap each other.

[0027] Specifically, the anomaly exclusion processing unit 13 (a1) derives a spatial luminance change distribution based on the luminance information, (a2) attempts to detect a region corresponding to an anomaly (here, a rectangular region circumscribing the anomaly within the detection region) based on the luminance change distribution, and (a3) ​​if the detection result of the region satisfies a predetermined condition and (b) the type of the above-mentioned certain anomaly and the type of the above-mentioned other anomaly are different from each other, excludes one of the above-mentioned certain anomaly and the above-mentioned other anomaly from the detected anomalies.

[0028] In addition, when the target image includes color information based on a predetermined color space (e.g., RGB data based on an RGB color space), the anomaly exclusion processing unit 13 may determine, for each color coordinate (e.g., R coordinate, G coordinate, and B coordinate) of the color space, whether or not the luminance information at the color coordinate of either the above-mentioned certain anomaly or the above-mentioned other anomaly satisfies a predetermined condition, and if (a) the predetermined condition is established (for any of the color coordinates) and (b) the type of the above-mentioned certain anomaly and the type of the above-mentioned other anomaly are different from each other, then the above-mentioned certain anomaly and one of the above-mentioned other anomaly may be excluded from the detected anomalies.

[0029] The abnormality handling processing unit 14 executes a predetermined abnormality handling process for the detected abnormality (other than the excluded abnormality). In other words, the abnormality handling process is not executed for the excluded abnormality. The abnormality handling process includes reporting each detected abnormality (reporting by sending a message via the communication device or displaying a message on the display device 4 to an operator who identifies the defective part corresponding to the abnormality or performs maintenance, etc.), identifying the defective part corresponding to each detected abnormality, performing maintenance operations, etc.

[0030] Next, a description will be given of the operation of the image processing device shown in Fig. 1. Fig. 4 is a flow chart illustrating the operation of the image processing device shown in Fig. 1.

[0031] First, the target image acquisition unit 11 acquires a target image (image data) (step S1). Next, the anomaly detection unit 12 detects anomalies contained in the acquired target image, generates characteristic information of the detected anomalies (position and size information, type, degree of anomaly, etc.), and stores it in a RAM or the like (step S2).

[0032] Next, the abnormality exclusion processing unit 13 executes an abnormality exclusion process for excluding a specific abnormality from the detected abnormalities (step S3).

[0033] The abnormality handling processor 14 executes a predetermined abnormality handling process for the detected abnormality (other than the excluded abnormality) (step S4).

[0034] Here, the abnormality exclusion process in step S3 will be described. Fig. 5 is a flowchart illustrating the abnormality exclusion process (step S3) in Fig. 2. Fig. 6 is a diagram illustrating an example of the abnormality exclusion process (step S3) in Fig. 2.

[0035] First, the anomaly exclusion processor 13 determines whether or not there is an overlap of anomalies (detection regions) among the detected anomalies (step S11). Specifically, the anomaly exclusion processor 13 selects the detected anomalies in order, and determines whether or not a part or all of the detection region of the selected anomaly overlaps with the detection region of any other anomaly based on the above-mentioned characteristic information, thereby detecting a pair of two overlapping anomalies (detection regions).

[0036] Then, when a pair of two overlapping abnormalities (detection regions) is detected, the abnormality exclusion processing unit 13 determines whether or not the types of the two overlapping abnormalities are different (step S12).

[0037] If it is determined that the types of the two overlapping anomalies are different, the anomaly exclusion processing unit 13 derives the luminance change distribution of the detection area of ​​at least a specific type of anomaly (here, a point anomaly) among the two anomalies (step S13).

[0038] Specifically, the anomaly exclusion processor 13 sequentially calculates differences in pixel values ​​(luminance values) between adjacent pixels in the detection region, and derives a luminance change distribution.

[0039] Then, the abnormality exclusion processor 13 attempts to detect a luminance change region based on the luminance change distribution (step S14).

[0040] Specifically, the anomaly exclusion processing unit 13 identifies a position in the brightness change distribution where the above-mentioned difference value (absolute value) is equal to or greater than a predetermined threshold, determines that the portion surrounded by that position is abnormal, and identifies the circumscribing rectangle of that portion as a brightness change area.

[0041] Here, if the abnormality exclusion processor 13 succeeds in detecting a luminance change region (step S15), it determines whether or not the luminance change region satisfies a predetermined condition (step S16).

[0042] For example, the predetermined condition is that the area or aspect ratio of the luminance changing region (rectangular region) is lower than a predetermined threshold value.

[0043] Then, when the luminance change area satisfies a predetermined condition, the anomaly exclusion processing unit 13 eliminates the corresponding anomaly (here, a point anomaly) (step S17).

[0044] In this way, a specific abnormality is excluded from the detected abnormalities. Note that if overlapping of different types of abnormalities is not detected in steps S11 and S12, if it is determined in step S15 that the detection of the luminance change area has not been successful, or if it is determined in step S16 that the luminance change area does not satisfy the predetermined condition, the above-mentioned exclusion of abnormalities is not executed.

[0045] For example, as shown in FIG. 6, for a point anomaly and a line anomaly that overlap each other, if a luminance change area is detected in the detection area corresponding to the point anomaly, the point anomaly is not removed, whereas if a luminance change area is not detected in the detection area corresponding to the point anomaly, the point anomaly is removed.

[0046] As described above, according to the above embodiment, anomaly detection unit 12 detects anomalies contained in a target image, and anomaly exclusion processing unit 13 excludes a specific anomaly from the detected anomalies. Then, when a detection area of ​​one anomaly among the detected anomalies overlaps with a detection area of ​​another anomaly, and the type of the one anomaly and the type of the other anomaly are different from each other, if the luminance information of one of the one anomaly and the other anomaly satisfies a predetermined condition, anomaly exclusion processing unit 13 excludes one of the one anomaly and the other anomaly from the detected anomalies.

[0047] This allows false anomalies to be excluded from the detected anomalies, improving the accuracy of anomaly detection, and ultimately reducing the calculation costs and processing time required for anomaly response processing.

[0048] It should be noted that various changes and modifications to the above-described embodiments will be apparent to those skilled in the art. Such changes and modifications may be made without departing from the spirit and scope of the subject matter and without diminishing its intended advantages. In other words, such changes and modifications are intended to be included within the scope of the claims. [Industrial Applicability]

[0049] The present invention is applicable, for example, to anomaly detection. [Explanation of symbols]

[0050] 1. Processing unit (an example of a computer) 12 Anomaly detection section 13 Abnormality exclusion processing unit

Claims

1. an anomaly detection unit that detects anomalies contained in a target image; an anomaly exclusion processing unit that excludes a specific anomaly from the detected anomalies, the anomaly exclusion processing unit, when a detection area of ​​one anomaly and a detection area of ​​another anomaly among the detected anomalies overlap and a type of the one anomaly and a type of the other anomaly differ from each other, excludes one of the one anomaly and the other anomaly from the detected anomalies when luminance information of one of the one anomaly and the other anomaly satisfies a predetermined condition; the anomaly exclusion processing unit (a1) derives a spatial luminance change distribution based on the luminance information, (a2) attempts to detect an area corresponding to the anomaly based on the luminance change distribution, (a3) ​​if a detection result of the area satisfies the predetermined condition, and (b) if a type of the certain anomaly and a type of the other anomaly are different from each other, excludes one of the certain anomaly and the other anomaly from the detected anomalies; An image processing device comprising:

2. the target image includes color information based on a predetermined color space; the anomaly exclusion processing unit determines, for each color coordinate in the color space, whether or not luminance information at the color coordinate of one of the one anomaly and the other anomaly satisfies the predetermined condition, and, if (a) the predetermined condition is established and (b) a type of the one anomaly and a type of the other anomaly are different from each other, excludes one of the one anomaly and the other anomaly from the detected anomalies; 2. The image processing device according to claim 1,

3. 3. The image processing apparatus according to claim 1, wherein one of the certain abnormality type and the other abnormality type is a point abnormality.

4. the anomaly detection unit detects the anomaly using a filter and generates characteristic information of the anomaly; The characteristic information includes a type of the abnormality; 4. The image processing device according to claim 1, further comprising:

5. An anomaly detection step of detecting an anomaly contained in a target image by a calculation processing device; and an anomaly excluding step of excluding a specific anomaly from the detected anomalies by the arithmetic processing device, In the anomaly exclusion step, when a detection area of ​​one anomaly and a detection area of ​​another anomaly among the detected anomalies overlap and the type of the one anomaly and the type of the other anomaly are different from each other, if luminance information of one of the one anomaly and the other anomaly satisfies a predetermined condition, one of the one anomaly and the other anomaly is excluded from the detected anomalies, In the anomaly exclusion step, (a1) a spatial luminance change distribution is derived based on the luminance information, (a2) a region corresponding to the anomaly is detected based on the luminance change distribution, (a3) ​​a detection result of the region satisfies the predetermined condition, and (b) when a type of the certain anomaly and a type of the other anomaly are different from each other, one of the certain anomaly and the other anomaly is excluded from the detected anomalies; An image processing method comprising:

6. causing the computer to function as an anomaly detection unit that detects anomalies contained in the target image and an anomaly exclusion processing unit that excludes specific anomalies from the detected anomalies; the anomaly exclusion processing unit, when a detection area of ​​one anomaly and a detection area of ​​another anomaly among the detected anomalies overlap and a type of the one anomaly and a type of the other anomaly differ from each other, excludes one of the one anomaly and the other anomaly from the detected anomalies when luminance information of one of the one anomaly and the other anomaly satisfies a predetermined condition; the anomaly exclusion processing unit (a1) derives a spatial luminance change distribution based on the luminance information, (a2) attempts to detect an area corresponding to the anomaly based on the luminance change distribution, (a3) ​​if a detection result of the area satisfies the predetermined condition, and (b) if a type of the certain anomaly and a type of the other anomaly are different from each other, excludes one of the certain anomaly and the other anomaly from the detected anomalies; An image processing program characterized by:

Images