Abstract: Provided are a density unevenness correction data creation method, a density unevenness correction data creation apparatus, a printing system, a program, a test chart, and a test chart data creation apparatus in which density unevenness correction with high accuracy is implemented. A captured image of a test chart including a density step pattern, an alignment mark, and a line mark is acquired, and in a case of acquiring correspondence relationship information between a theoretical position and an imaging position from the captured image, a rough correspondence relationship is acquired by using positional information of the alignment mark, a detailed correspondence relationship is acquired by using positional information of the line mark estimated by using the rough correspondence relationship, and density unevenness correction data is created by estimating a density value of each position of the density step pattern by using the detailed correspondence relationship.

Abstract: There is provided a machine learning model generation device, a machine learning model generation method, a program, an inspection device, an inspection method, and a printing device for inspecting a defect of a printed matter with high accuracy. A machine learning model for detecting the defect of the printed matter is generated by using, as learning input information, at least learning inspection data based on a captured image obtained by capturing an image of a printed matter as an inspection target and second learning reference data based on print digital data and using, as learning output information, at least learning defect information of the learning inspection data estimated by performing comparison processing of the learning inspection data and first learning reference data based on a captured image obtained by capturing the image of the printed matter.

Abstract: There is provided a machine learning model generation device, a machine learning model generation method, a program, an inspection device, an inspection method, and a printing device for inspecting a defect of a printed matter with high accuracy. A machine learning model for detecting the defect of the printed matter is generated by using, as learning input information, at least learning inspection data based on a captured image obtained by capturing an image of a printed matter as an inspection target and second learning reference data based on print digital data and using, as learning output information, at least learning defect information of the learning inspection data estimated by performing comparison processing of the learning inspection data and first learning reference data based on a captured image obtained by capturing the image of the printed matter.

Abstract: The image inspection method includes: a step of acquiring data of an inspection image obtained by capturing an image of a recorded matter recorded by an image recording system that performs a compensation process of compensating for a defect caused by a failure in an image formation element, using an imaging apparatus; a step of acquiring data of a reference image; and a step of comparing the data of the inspection image with the data of the reference image to determine whether there is a defect at each position of the inspection image. The defect detection step includes a process that makes a defect detection performance different in a compensation application region and a compensation non-application region other than the compensation application region, on the basis of compensation position information of the failure in the image formation element to which the compensation process has been applied.

Abstract: At least a part of an inspection image is divided into a finite number of local regions by allowing overlap in a first direction. A streak intensity signal quantitatively showing intensity of a streak for a position in a second direction intersecting with the first direction is created for each of the local regions. A position of a streak-like signal is detected by using each of at least one of T thresholds, where T is 1 or more. Presence or absence of a streak is determined for a position in accordance with the number of times of detection for each of thresholds in a local region group composed of two or more local regions connecting in the first direction. The number of times of detection required for determining that there is a streak for at least one of the thresholds is two or more.

Abstract: The image inspection method includes: a step of acquiring data of an inspection image obtained by capturing an image of a recorded matter recorded by an image recording system that performs a compensation process of compensating for a defect caused by a failure in an image formation element, using an imaging apparatus; a step of acquiring data of a reference image; and a step of comparing the data of the inspection image with the data of the reference image to determine whether there is a defect at each position of the inspection image. The defect detection step includes a process that makes a defect detection performance different in a compensation application region and a compensation non-application region other than the compensation application region, on the basis of compensation position information of the failure in the image formation element to which the compensation process has been applied.

Abstract: Provided are image inspection method and apparatus, and an ink jet printing apparatus that can highly accurately detect a stripe defect. An inspection image obtained by an imaging device imaging a printed matter printed by an ink jet printing apparatus including a line head is acquired. Each of at least one non-scanning direction linear structural element that is a linear structural element in a direction not parallel to a direction of scanning by the line head relative to a medium is used to execute morphology processing of a grayscale image to thereby smooth the inspection image to create a first smoothed inspection image (S22, S24). A stripe defect extending in the scanning direction is detected by using at least (1) one of the inspection image and a second smoothed inspection image created based on the inspection image and (2) the first smoothed inspection image.

Abstract: At least a part of an inspection image is divided into a finite number of local regions by allowing overlap in a first direction. A streak intensity signal quantitatively showing intensity of a streak for a position in a second direction intersecting with the first direction is created for each of the local regions. A position of a streak-like signal is detected by using each of at least one of T thresholds, where T is 1 or more. Presence or absence of a streak is determined for a position in accordance with the number of times of detection for each of thresholds in a local region group composed of two or more local regions connecting in the first direction. The number of times of detection required for determining that there is a streak for at least one of the thresholds is two or more.

Abstract: Provided are a signal conversion method and apparatus, a recording medium storing non-transitory program, and a print system which can prevent a color reproduction gamut from being excessively narrowed while avoiding a print failure caused by excess color material. A signal conversion method for limiting the total amount of color materials used in a printing device that forms an image on a recording medium using a plurality of color materials includes determining a final output vector after the total amount of color materials used is limited for an input vector, on the basis of a plurality of input/output signal conversion processes based on different limit values of the total amount of color materials used and weight definition information in which weights applied to the conversion results of the plurality of input/output signal conversion processes are determined according to the input vector.

Abstract: The test image is formed in accordance with input data in which a plurality of recording elements selected every N (an integer of 1 or more) pieces in a projected recording element group is indicated as a first recording element and a recording element that is not selected as the first recording element is indicated as a second recording element, the input data allowing: a first-stage pattern to be formed in a recording area of the second recording element in accordance with a second input gradation value; a recording position in the second direction to be sequentially changed; and the first recording element and the second recording element to be sequentially switched to form a second-stage pattern to an (N+1)-th-stage pattern.

Abstract: Provided are image inspection method and apparatus, and an ink jet printing apparatus that can highly accurately detect a stripe defect. An inspection image obtained by an imaging device imaging a printed matter printed by an ink jet printing apparatus including a line head is acquired. Each of at least one non-scanning direction linear structural element that is a linear structural element in a direction not parallel to a direction of scanning by the line head relative to a medium is used to execute morphology processing of a grayscale image to thereby smooth the inspection image to create a first smoothed inspection image (S22, S24). A stripe defect extending in the scanning direction is detected by using at least (1) one of the inspection image and a second smoothed inspection image created based on the inspection image and (2) the first smoothed inspection image.

Abstract: The test image is formed in accordance with input data in which a plurality of recording elements selected every N (an integer of 1 or more) pieces in a projected recording element group is indicated as a first recording element and a recording element that is not selected as the first recording element is indicated as a second recording element, the input data allowing: a first-stage pattern to be formed in a recording area of the second recording element in accordance with a second input gradation value; a recording position in the second direction to be sequentially changed; and the first recording element and the second recording element to be sequentially switched to form a second-stage pattern to an (N+1)-th-stage pattern.

Abstract: Provided are a signal conversion method and apparatus, a recording medium storing non-transitory program, and a print system which can prevent a color reproduction gamut from being excessively narrowed while avoiding a print failure caused by excess color material. A signal conversion method for limiting the total amount of color materials used in a printing device that forms an image on a recording medium using a plurality of color materials includes determining a final output vector after the total amount of color materials used is limited for an input vector, on the basis of a plurality of input/output signal conversion processes based on different limit values of the total amount of color materials used and weight definition information in which weights applied to the conversion results of the plurality of input/output signal conversion processes are determined according to the input vector.

Abstract: The present invention provides an image recording method and apparatus and a recording medium therefor. In an aspect of the present invention, when recording the image in a condition where an image recording range in a first direction by the image recorder is a specific range, image processing is applied to the image data using a latest image processing parameter among image processing parameters which are according to positions in the first direction and have been generated on the basis of measurement results of test charts output using the specific range or a wider range than the specific range on the image recorder, and the image recorder is caused to record the image on the recording medium according to the image data after the image processing.

Abstract: Unevenness correcting information is generated based on property information indicating a recording property of each of a plurality of recording elements which are included in a recording head, the recording elements being subjected to output correction in a first output correction unit based on unevenness correcting information obtained after a flattening processing and output correction in a second output correction unit, and the unevenness correcting information close to an appropriate value with which an image in an appropriately-corrected state can be obtained can be generated.

Abstract: The present invention provides an image recording method and apparatus and a recording medium therefor. In an aspect of the present invention, when recording the image in a condition where an image recording range in a first direction by the image recorder is a specific range, image processing is applied to the image data using a latest image processing parameter among image processing parameters which are according to positions in the first direction and have been generated on the basis of measurement results of test charts output using the specific range or a wider range than the specific range on the image recorder, and the image recorder is caused to record the image on the recording medium according to the image data after the image processing.

Abstract: Unevenness correcting information is generated based on property information indicating a recording property of each of a plurality of recording elements which are included in a recording head, the recording elements being subjected to output correction in a first output correction unit based on unevenness correcting information obtained after a flattening processing and output correction in a second output correction unit, and the unevenness correcting information close to an appropriate value with which an image in an appropriately-corrected state can be obtained can be generated.

Abstract: There is provided a technique of enabling the use of a common printer profile even in a case where a configuration of a printer system is changed or added. Color data under a second configuration condition corresponding to an output color which matches or approximates an output color acquired through a first color predictor under a first configuration condition, is searched and acquired from color data subjected to total color material amount restriction processing acquired by total color material amount restriction processing using a first color material amount restriction profile under the first configuration condition, through a second color predictor under the second configuration condition. The color data searched and acquired under the second configuration condition and color data prior to total color material amount restriction processing are associated and a second total color material amount restriction profile under the second configuration condition is created.

Abstract: According to the present invention, it is possible to adequately restrict the total color material amount from the viewpoint of the second scale which substantially represents a color material amount, and sufficiently produce the color reproducibility which is potentially held by an image formation apparatus. Moreover, since the order of the CMY ratio in the space of the first scale is maintained, it is possible to smoothly secure the connection between tones.

Abstract: According to the present invention, even if the coloring material use amount is limited but ambiguities remain and an accurate coloring material use limit is not known, then a virtual coloring material use limit is set artificially, the color measurement values of virtual patches in a region that exceeds the coloring material use limit are inferred by extrapolation and the color measurement values in the region exceeding the coloring material use limit are predicted by interpolation using the inferred color measurement values. Therefore, it is possible to predict colors in relation to any input exceeding the coloring material use limit.