JP4285253B2 - Image inspection device with tilt detection function - Google Patents

Description

  The present invention relates to an image inspection apparatus that acquires inspection image data by reading a sheet on which document image data has been printed, and compares the inspection image data with document image data to inspect a print state. In particular, the present invention relates to an image inspection apparatus that detects an inclination of inspection image data by a printing process.

  In a printer, a copier, a facsimile machine, or a digital multi-function peripheral having these functions (hereinafter collectively referred to as an image forming apparatus), original image data input to the apparatus is a sheet (here, a sheet is referred to as a sheet). In general, it is a printing medium in general, and is a concept including OHP sheets, cardboard, postcards, etc. in addition to general paper), and provides printed matter to the user. During the printing process, the paper taken out from the paper feeding device is sent on the conveyance path by the paper feeding mechanism, and the printing unit, the fixing unit, etc. cooperate with each other to perform the printing operation.

  The printed matter obtained by the above printing process may have a skew (tilt) as a whole when compared with the original image data. A typical cause of the skew is that the sheet is slightly inclined on the conveyance path. Of course, such an inclination of the printed matter is not preferable, and sometimes the printed matter is discarded as a printing mistake. For this reason, attempts have been made to detect skew of printed matter, and examples thereof are described in Japanese Patent No. 3038714, Japanese Patent No. 3303246, Japanese Patent Application Laid-Open No. 2002-84420, and the like.

  In the technique described in Japanese Patent No. 3038714, when image data is acquired by reading a printed matter with an image scanner or the like, the image data is sequentially rotated by an angle θ. At this time, a circumscribed rectangle including all black pixels is generated for each rotated image data, and the area of the circumscribed rectangle is obtained. Then, the angle θ at which the area of the circumscribed rectangle is minimized is detected as the skew angle of the printed matter.

  However, in the above-described processing, the amount of calculation processing required for the rotation processing of the inspection image data and the generation processing of the circumscribed rectangle is large, and the processing time until the skew angle is detected is long. In addition, when the printed content of the printed matter is approximately rectangular, the skew angle detection accuracy can be made relatively high. However, when the printed content has a shape other than the rectangular shape, the skew angle is detected. There was a problem that the accuracy might decrease.

  In the technology described in Japanese Patent No. 3303246, a circumscribed rectangle is created while examining connectivity of black pixels included in an image, and only a circumscribed rectangle having a size in a predetermined range is extracted, and the extracted circumscribed rectangle is extracted. Histograms obtained by projecting one vertex of the image in various directions are obtained, and an angle at which the histogram is maximum is detected as a skew angle.

  However, in the above processing, since the skew angle is detected from the projection histogram of the circumscribed rectangle vertices, the document image is composed of multi-column text areas, and the line position between the columns is shifted accurately. There was a problem that the skew angle could not be detected. In addition, since the technique is basically intended for the character area, there is a problem that the skew angle cannot be detected accurately even when the number of characters included in the document image is small.

  In the technique described in Japanese Patent Application Laid-Open No. 2002-84420, a binarized image is subjected to a Hough transform, Hough space data is generated, a histogram is created by projecting the Hough space data for each angle, and the maximum value of the histogram Is detected as a skew angle.

Japanese Patent No. 3038714 Japanese Patent No. 3303246 JP 2002-84420 A

  An object of the present invention is to detect the skew angle of inspection image data with respect to document image data with high accuracy without being affected by the shape of the printed content of the printed matter.

  Another object of the present invention is to quickly detect a skew angle of inspection image data with respect to a document image with a small amount of calculation processing.

  In order to achieve the above-described object, the present invention is an image inspection apparatus for inspecting a printed material on which original image data is printed, and an inspection image acquisition unit for acquiring inspection image data obtained by imaging the printed material; Screen information detecting means for detecting screen related information from the inspection image data, and inclination detecting means for obtaining a skew angle of the inspection image data with respect to the original image data based on the screen related information. Features.

  Further, the screen information detection unit detects a screen angle of the inspection image data, and the inclination detection unit obtains a difference between the screen angle of the inspection image data and the screen angle of the document image data as a skew angle. preferable.

  Further, it is preferable that the image processing apparatus further includes an area extracting unit that searches and extracts a halftone area included in the inspection image data, and the screen information detecting unit detects a screen angle in the halftone area. Here, it is preferable that the region extracting means searches and extracts a halftone region having a predetermined halftone dot area ratio. Further, it is preferable that the area extracting means searches for and extracts a halftone area including a line screen having a predetermined thickness. Further, it is preferable that the area extracting means searches for and extracts a monochrome halftone area. Further, it is preferable that the region extracting means searches and extracts a halftone region having a predetermined area or more.

  The screen information detecting means preferably detects the screen angle based on the spatial frequency of the feature point obtained by two-dimensional Fourier transform of the inspection image data. Here, it is preferable that a means for thinning out the pixel data of the inspection image data is provided according to the number of screen lines per unit length.

  Preferably, the screen information detection unit detects a screen moire of the inspection image data, and the inclination detection unit obtains a skew angle of the inspection image data based on the screen moire of the inspection image data. Here, it is preferable that the inclination detection unit obtains a skew angle of the inspection image data by multiplying a deviation of the moire angle by a predetermined constant.

  In order to achieve the above-described object, the present invention provides an image forming apparatus that prints original image data, images a printed matter, and obtains inspection image data, and inspection image data from the inspection image data. Screen information detecting means for detecting screen related information, and inclination detecting means for obtaining a skew angle of the inspection image data with respect to the original image data based on the screen related information. Here, it is preferable to provide a sheet-like member that is provided close to the printing surface of the printed matter and on which a predetermined screen is fixed.

  In order to achieve the above-described object, the present invention is an image inspection method for inspecting a printed matter on which original image data is printed, and obtains inspection image data by imaging the printed matter, and screen-related from the inspection image data. Information is detected, and a skew angle of the inspection image data with respect to the document image data is obtained based on the screen related information.

  In order to achieve the above-described object, the present invention provides an image inspection apparatus for inspecting a printed material on which original image data is printed, an inspection image acquisition step of acquiring inspection image data obtained by imaging the printed material, Image inspection for executing a screen information detecting step for detecting screen related information from inspection image data, and an inclination detecting step for obtaining a skew angle of the inspection image data with respect to the original image data based on the screen related information. It is a program.

  Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram illustrating an example of a printing system including an image inspection apparatus according to the first embodiment.

  In this printing system, when document image data is fetched from the outside, the print processing unit 20 prints an image on the sheet fed from the sheet feeding cassette 10, and the printed document image is fixed on the sheet by the fixing roller 25. . In the case of an electrophotographic system, the print processing unit 20 includes a raster output scanner, a photosensitive drum, a developing device, a transfer roll, and the like.

  A reading scanner 30 is provided downstream of the fixing roller 25 in the paper conveyance path. The printed surface of the printed material on which the image is fixed is optically read by the reading scanner 30. The reading scanner 30 irradiates the printing surface with an irradiation lamp 35, focuses the reflected light with a lens 36, and detects it with an imaging device 37. As the imaging device 37, for example, a line sensor in which cells are arranged in a line in a direction perpendicular to the paper conveyance direction in a plane parallel to the upper surface of the paper conveyance path can be used. By repeatedly reading the line sensor in synchronization with the sheet conveyance, a two-dimensional printed surface image can be acquired. When inspecting a color image, for example, a line sensor may be provided for each of R, G, and B colors. The image data of the printing surface acquired by the imaging device 37, that is, the inspection image data is sent to the image processing apparatus 50. Note that the reading resolution of the line sensor is determined in consideration of the accuracy and processing speed necessary for the inspection, and 40 dpi or more is appropriate, but in this embodiment, it is 600 dpi.

  The image inspection apparatus according to this embodiment includes a reading scanner 30 and an image processing apparatus 50. The image processing apparatus 50 includes a CPU, a memory, and the like. The CPU executes an image inspection program to detect a skew angle of the inspection image with respect to the document image, and corrects the inspection image based on the skew angle. The inspection image is compared with the document image to detect a print defect. FIG. 2 is a flowchart showing processing performed by the image processing apparatus 50.

  First, the image processing apparatus 50 selects a halftone area composed of halftone dots suitable for skew angle detection in the document image data, and extracts a part of the halftone area as a partial area for screen angle detection (S201). ). Here, in the halftone area, an area satisfying the following search conditions 1 to 3 is searched and extracted in order to detect the skew angle suitably.

  Condition (1) The dot area ratio is such that the screen is clearly imaged by the reading scanner 30. Here, the halftone dot area ratio is the proportion of halftone dots in the region. In the present embodiment, when the halftone dot area ratio is close to 100%, adjacent halftone dots are combined with each other, and the screen is not clearly imaged. Therefore, a region having a halftone dot area ratio of 90% or less is extracted. . In this embodiment, the case where the screen is configured with halftone dots is taken as an example. However, even when the screen is a line screen, a region with a predetermined area ratio may be similarly searched. As a result, a line screen having a thickness suitable for detecting the skew angle can be extracted.

  Condition (2) Having a predetermined area necessary for detecting the screen angle. In other words, since the screen angle is calculated from the geometric relationship between the positions of a plurality of adjacent halftone dots, the halftone area must be equal to or larger than a predetermined area that necessarily includes a plurality of halftone dots necessary for calculating the screen angle. . This area is determined by the number of screen lines (lpi), screen angle (degree), desired skew angle detection accuracy, and the like.

  Condition (3) A single color area. That is, in the multi-color region, the halftone dots of the respective colors are arranged at different screen angles, which makes it difficult to detect the screen angle. Therefore, by selecting a monochromatic area, the screen angle detection process is simplified.

  When a plurality of areas are searched as areas satisfying the above search conditions, the area with the largest area is extracted in order to improve the accuracy of skew angle detection.

  In addition, when the printing system is provided with a function for the user to select a screen setting according to his / her preference from a plurality of types of screens, the search condition can be switched according to the selected screen setting. May be.

  FIG. 3 shows the result of extracting a partial area that meets the above conditions from a document image. This partial region is a cluster dot screen with a screen angle of 26.6 degrees and a dot area ratio of 50%. The image resolution is 600 dpi and the image size is 512 × 512 pixels.

  Next, the halftone area extracted in step S201 and the partial area having the same coordinates are extracted from the inspection image (S202). FIG. 4 shows a result of extracting a partial area from a printed image obtained by printing original image data at 600 dpi by the printing system from an inspection image read by the imaging device 37 at 600 dpi. The image size is 512 × 512 pixels. 3 and 4, the horizontal direction is the x direction and the vertical direction is the y direction.

  Next, a two-dimensional Fourier transform process is performed on each partial area extracted from the document image and the inspection image (S203). FIG. 5 shows a Fourier transform spectrum image obtained by performing two-dimensional Fourier transform processing on a partial region of the original image, and FIG. 6 shows a Fourier transform image obtained by performing two-dimensional Fourier transform processing on the partial region of the inspection image. . In each Fourier transform image, the horizontal axis is the spatial frequency s in the x direction, and the vertical axis is the spatial frequency t in the y direction. A point indicating a direct current component exists at the origin (0, 0) of the center of the Fourier transform image, and a point indicating the periodicity of the original image and the inspection image exists around the point. In the present embodiment, fast Fourier transform (FFT) is used for Fourier transform.

Next, from the Fourier transform image of the document image, two points that are point-symmetric with respect to the origin among the plurality of points are selected as feature points for calculating the screen angle. Then, the screen angle θorg is calculated by performing the following calculation on these two points (S204).
Here, s ₁ is the s-direction distance between two feature points in the Fourier transform image, and t ₁ is the t-direction distance between the two feature points.

Similarly, two feature points are extracted and selected from the Fourier transform image of the inspection image data, and the screen angle θcap is calculated by performing the following calculation. Note that the two points extracted from the Fourier transform image of the inspection image data are substantially in the same position as the two points extracted from the Fourier transform image of the document image data.
Here, s ₂ is the s-direction distance between two feature points in the Fourier transform image, and t ₂ is the t-direction distance between the two feature points.

Further, the skew angle θ of the inspection image with respect to the original image when the original image is used as a reference is obtained by performing the following calculation using the screen angles θorg and θcap calculated by the above processing.

Further, when obtaining the skew angle θ ′ with the inspection image as a reference, the following calculation is performed.

Next, the skew angle is corrected by rotating the inspection image based on the skew angle θ of the inspection image with respect to the document image (S205). Here, the following processing is performed on the coordinate value (x, y) of each pixel of the inspection image to obtain the rotated coordinate value (u, v).

In the above-described processing, the inspection image is rotated. However, the skew angle may be corrected by rotating the document image. In this case, the following processing is performed on the coordinate value (x, y) of each pixel of the document image.

  Next, a known template matching process is performed on the document image and the inspection image to align the document image and the inspection image. Here, as the known template matching, for example, a residual sequential test method or the like may be used. Then, after the alignment, the pixel values of the respective pixels at the same coordinates are compared to perform image collation, and a print defect included in the inspection image is detected (S206). Thereby, the presence or absence of the printing defect of printed matter is determined.

  In step S201, if the original image does not have a halftone area having a halftone dot suitable for detection of the skew angle, template matching is performed without detecting the processing of S202 to S205, and a printing defect is detected.

  The characteristic matter of the present embodiment described above is that the screen angle of the original image and the inspection image is detected and compared to calculate the skew angle of the inspection image with respect to the original image. Thus, the skew angle of the inspection image can be detected with high accuracy without being influenced by the shape of the print content. Further, since the above-described process is a simple process, it is possible to quickly calculate the skew angle and detect a printing defect.

  In this embodiment, the screen angle of the original image and the inspection image is obtained and the skew angle is calculated by comparing them. However, the screen angle of the original image may be known depending on the color and the print mode in the printing system. is there. In such a case, the skew angle may be calculated by obtaining only the screen angle of the inspection image and comparing it with the screen angle of the known document image.

  In this embodiment, the resolution (dpi) of the original image and the inspection image is surely set to be twice or more the screen line number (lpi) in order to prevent erroneous detection of the screen angle. That is, the number of screen lines varies depending on the color, print mode, etc., but the resolution is at least twice the maximum number of screen lines. Note that it is known from the sampling theorem that there is a possibility of erroneous detection when the resolution is less than twice the number of screen lines.

  Since the resolution conversion affects the skew angle detection accuracy and collation accuracy, it is not indispensable. However, as a modification of the present embodiment, the original image data and the inspection are based on the information on the number of screen lines in the extracted partial area. Means for reducing the resolution by thinning out the pixel data of the image data may be provided. For example, when the screen line number is about 100 lpi, false detection does not occur even if the resolution of the original image data and the inspection image data is about 300 dpi. . Thereby, since the data amount of each image data decreases, the process in the image processing apparatus 50 can be simplified.

  Further, as another modification of the present embodiment, when the printing system is provided with a function for the user to select a screen setting according to his / her preference, the printing system is set according to the maximum screen line number of the selected screen setting. A means for reducing the resolution by thinning out the pixel data of the original image data and the inspection image data may be provided. This also simplifies the processing of the image processing apparatus 50.

  In this embodiment, the screen angle is detected by performing Fourier transform on the inspection image data and the document image data. However, in other embodiments, the screen angle may be obtained by another method. For example, when the screen is a line screen, one screen may be extracted, and the screen angle may be calculated from pixel coordinates of a plurality of points including at least two points included in the screen.

  Next, a printing system including the image inspection apparatus according to the second embodiment will be described. FIG. 7 is a configuration diagram illustrating an example of a printing system including an image inspection apparatus according to the second embodiment. In the second embodiment, the skew angle of the inspection image is detected using moire generated in the inspection image.

  The printing system according to the second embodiment has a first reading scanner 32 and a second reading scanner 30. The configuration of the second reading scanner 30 is the same as that of the first embodiment. FIG. 8 shows the internal configuration of the first reading scanner 32. In the first reading scanner 32, an image pickup device 37, a lens 36, and an irradiation lamp 35 are arranged in the same manner as the second reading scanner 30, and a sheet-like member 38 made of a material that transmits light is a paper conveyance path. Are arranged along. A fixed screen pattern which is a predetermined line screen (spatial frequency f1, screen angle θ1) is fixed on the surface of the sheet-like member 38. When the printed matter 40 is imaged, the printed matter 40 overlaps the sheet-like member 38, and as a result, moire occurs in the inspection image captured by the imaging device 37.

  FIG. 9 is a flowchart illustrating processing performed by the image processing apparatus 50. First, the image processing apparatus 50 searches and extracts a region that satisfies the following search conditions 1 to 3 in order to suitably detect a skew angle in a document image.

  Condition (1) The dot area ratio is such that the screen is clearly imaged by the reading scanner 30. Here, the halftone dot area ratio is the proportion of halftone dots in the region. In the present embodiment, when the halftone dot area ratio is close to 100%, adjacent halftone dots are combined with each other, and the screen is not clearly imaged. Therefore, a region having a halftone dot area ratio of 90% or less is extracted. . In this embodiment, the case where the screen is configured with halftone dots is taken as an example. However, even when the screen is a line screen, a region with a predetermined area ratio may be similarly searched. As a result, a line screen having a thickness suitable for detecting the skew angle can be extracted.

  Condition (2) Having a predetermined area necessary for detecting the screen angle. In other words, since the screen angle is calculated from the geometric relationship between the positions of a plurality of adjacent halftone dots, the halftone area must be equal to or larger than a predetermined area that necessarily includes a plurality of halftone dots necessary for calculating the screen angle. . This area is determined by the number of screen lines (lpi), screen angle (degree), desired skew angle detection accuracy, and the like.

  Condition (3) A single color area. That is, in the multi-color region, the halftone dots of the respective colors are arranged at different screen angles, which makes it difficult to detect the screen angle. Therefore, by selecting a monochromatic area, the screen angle detection process is simplified.

  When a plurality of areas are searched as areas satisfying the above search conditions, the area with the largest area is extracted in order to improve the accuracy of skew angle detection.

  In addition, when the printing system is provided with a function for the user to select a screen setting according to his / her preference from a plurality of types of screens, the search condition can be switched according to the selected screen setting. May be.

  Next, a partial area having the same coordinates as the selected halftone area is extracted from the inspection image read from the first reading scanner 32 (S802). FIG. 10 shows the extracted partial areas. Since the printed material is skewed, the screen of the printed material and the fixed screen pattern influence each other, and a moire stripe pattern is generated in a partial region of the inspection image.

  Next, the extracted partial area is blurred by a smoothing filter, and as shown in FIG. 11, a large pixel value change due to the line screen is removed (S803). As a result, only the moire stripe pattern remains in the partial area. Next, the inclination angle θ3 of the moire stripe pattern is obtained (S804). Here, in order to obtain the moire inclination angle θ3, a known method such as binarization of the image of FIG. 11 to obtain the direction of the boundary line between the black region and the white region, or a Hough transform process may be used. .

  Next, a deviation Δφ of the moire angle θ3 from the screen angle θ2 is obtained, and the deviation Δφ is multiplied by a constant (f1-f2) / f2, and the calculation result is detected as a skew angle Δθ (S805). Subsequent skew angle correction is the same as in the first embodiment (S806).

  A characteristic matter of the present embodiment is that a skew angle is detected by detecting a moire angle. As described above, the deviation of the moire angle is a value obtained by amplifying the skew angle. Therefore, when the skew angle is very small, the skew angle can be detected more accurately by detecting a moire angle that is relatively easy to detect.

  Next, a known template matching process is performed on the original image and the inspection image read by the second reading scanner 30 to align the original image and the inspection image. Here, as the known template matching, for example, a residual sequential test method or the like may be used. After the alignment, the pixel values of the respective pixels at the same coordinates are compared to perform image collation, and a print defect included in the inspection image is detected (S807). Thereby, the presence or absence of the printing defect of printed matter is determined.

  In the above-described detection process of the skew angle Δθ, the deviation Δφ is obtained by utilizing the fact that the moire angle Δφ and the skew angle Δθ are in a linear relationship. In this linear relationship, a description will be given of the fact that the skew angle Δθ can be obtained by multiplying the deviation Δφ of the moire angle θ3 from the screen angle θ2 by a constant (f1-f2) / f2.

When the reflectance distribution and transmittance distribution of the screen of the partial region of the printed matter and the screen of the sheet-like member are approximated to a sine wave shape, the two composite R (x, y) are expressed by the following equations.
In the above equation, the term of the following equation relates to moire.
Here, the relationship of the following expression is established for the spatial frequency f3 and the angle θ3 of the moire.
Therefore, the following relationship is obtained.
It can be seen that the moire spatial frequency f3 is calculated by the following equation by squaring and adding both sides of the above two equations.
It can also be seen that the moire angle θ3 is calculated by the following equation.

Furthermore, when Δf = f1−f2, Δθ = θ1−θ2, and Δφ = θ3−θ2, Equation 12 is expressed by the following equation.
Here, by expanding the right side of Equation 13, the relationship of the following equation is obtained.
Further, from the trigonometric function formula, the following relationship is obtained for the left side of Equation 13.
Since Formula 14 and Formula 15 are equal, the following formula is obtained.
Therefore, the following equation is obtained.
The fact that the moire angle and the skew angle are in a linear relationship can be understood from the development of the above formula, and the constant multiplied by the deviation Δφ is (f1−f2) / f2.

Here, the results of calculating the spatial frequency f3 and the angle θ3 of the moire using the formulas 11 and 12 are shown in the following table.

  In this calculation, the spatial frequency f2 = 141.42 lpi and the angle θ2 = 45 deg are set as conditions for the fixed screen pattern, and the spatial frequency f1 = 1121.22 lpi is set as the condition for the screen of the printed matter. Then, the screen angle θ1 is changed around 45 degrees assuming a skew of the printed matter.

Also from this calculation result, it can be seen that a linear relationship is established in a minute range where the skew angle Δθ is about ± 2 deg, and the moire deviation Δφ is about seven times the skew angle Δθ.

Substituting the spatial frequencies f2 and f3 into Expression 17, the following expression is obtained. Also from the following equation, it can be seen that the moire deviation Δφ is about seven times the skew angle Δθ.

  The preferred embodiments of the present invention have been described above. However, the present invention is not limited to the above embodiments, and various modifications can be made within an equivalent range.

1 is a configuration diagram of a printer system. FIG. It is a flowchart of a process of an image inspection apparatus. It is explanatory drawing which shows the halftone area extracted from the original image. It is explanatory drawing which shows the halftone area extracted from the test | inspection image. It is explanatory drawing which shows the Fourier-transform image of the halftone area | region of a document image. It is explanatory drawing which shows the Fourier-transform image of the halftone area | region of a test | inspection image. It is a block diagram of the printer system of 2nd embodiment. It is a block diagram of the reading scanner of 2nd embodiment. It is a flowchart of the process of 2nd embodiment. It is explanatory drawing which shows the partial area | region of a test | inspection image. It is explanatory drawing which shows the partial area | region of the test | inspection image smoothed.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 Paper cassette, 20 Print processing part, 25 Fixing roller, 30 Reading scanner, 35 Irradiation lamp, 36 Lens, 37 Imaging device, 38 Sheet-like member, 50 Image processing apparatus.

Claims (12)

An image inspection apparatus for inspecting a printed matter on which original image data is printed,
Inspection image acquisition means for acquiring inspection image data obtained by imaging a printed matter;
Screen information detecting means for detecting screen related information from the inspection image data;
Inclination detecting means for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen related information;
Area extraction means for searching and extracting a halftone area included in the inspection image data;
Equipped with a,
The screen information detecting means detects a screen angle in the halftone region of the inspection image data;
The inclination detecting means obtains a difference between the screen angle of the inspection image data and the screen angle of the document image data as a skew angle.
An image inspection apparatus with an inclination detection function. The image inspection apparatus according to claim 1 ,
The image extracting apparatus according to claim 1, wherein the area extracting unit searches for and extracts a halftone area having a predetermined halftone dot area ratio. The image inspection apparatus according to claim 1 ,
The image extracting apparatus according to claim 1, wherein the area extracting unit searches and extracts a halftone area including a line screen having a predetermined thickness. The image inspection apparatus according to claim 1 ,
The image extracting apparatus according to claim 1, wherein the area extracting unit searches and extracts a monochrome halftone area. The image inspection apparatus according to claim 1 ,
The image extracting apparatus according to claim 1, wherein the area extracting unit searches and extracts a halftone area having a predetermined area or more. An image inspection apparatus for inspecting a printed matter on which original image data is printed,
Inspection image acquisition means for acquiring inspection image data obtained by imaging a printed matter;
Screen information detecting means for detecting screen related information from the inspection image data;
Inclination detecting means for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen related information;
With
The screen information detecting means detects a screen angle of the inspection image data;
The inclination detecting means obtains a difference between a screen angle of the inspection image data and a screen angle of the document image data as a skew angle,
It said screen information detecting means, an image inspection apparatus and detects the screen angle based on the spatial frequency of the resulting feature point by the two-dimensional Fourier transform of the test image data. The image inspection apparatus according to claim 6 ,
An image inspection apparatus comprising means for thinning out pixel data of the inspection image data according to the number of screen lines. An image inspection apparatus for inspecting a printed matter on which original image data is printed,
Inspection image acquisition means for acquiring inspection image data obtained by imaging a printed matter;
Screen information detecting means for detecting screen related information from the inspection image data;
Inclination detecting means for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen related information;
With
The screen information detecting means detects a screen moire of the inspection image data,
The image inspection apparatus, wherein the inclination detecting unit obtains a skew angle of the inspection image data based on a screen moire of the inspection image data. The image inspection apparatus according to claim 8 ,
The inclination detecting means obtains a skew angle of the inspection image data by multiplying a deviation of the moire angle by a predetermined constant. An image forming apparatus that prints original image data,
Inspection image acquisition means for imaging a printed material and acquiring inspection image data;
Screen information detecting means for detecting screen related information from the inspection image data;
Inclination detecting means for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen related information;
With
An image forming apparatus comprising a sheet-like member that is provided close to a printing surface of a printed matter and on which a predetermined screen is fixed. An image inspection method for inspecting a printed matter on which original image data is printed,
An inspection image acquisition step of capturing a printed material and acquiring inspection image data;
A region extracting step of searching and extracting a halftone region included in the inspection image data;
A screen information detection step of detecting screen-related information from the inspection image data;
An inclination detection step for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen-related information ;
Including
In the screen information detection step, a screen angle in the halftone region of the inspection image data is detected,
In the tilt detection step, a difference between the screen angle of the inspection image data and the screen angle of the document image data is obtained as a skew angle.
An image inspection method characterized by the above. In an image inspection device that inspects printed matter on which original image data is printed,
An inspection image acquisition step of acquiring inspection image data obtained by imaging a printed matter;
A region extracting step of searching and extracting a halftone region included in the inspection image data;
A screen information detection step of detecting screen-related information from the inspection image data;
An inclination detecting step for obtaining a skew angle of the inspection image data with respect to the document image data based on the screen-related information;
An image inspection program for execution,
In the screen information detection step, a screen angle in the halftone region of the inspection image data is detected,
In the tilt detection step, a difference between the screen angle of the inspection image data and the screen angle of the document image data is obtained as a skew angle.
An image inspection program characterized by that.