Abstract: A system that uses a learning module to realize execution of a predetermined task includes: a first input unit configured to receive information acquired from one or more external systems, and generate at least a portion of information to be input to the learning module; an output unit configured to acquire information output from the learning module, and generate information to be output from the system, the information output from the system being information based on which execution of a predetermined task is to be realized; and a second input unit configured to receive an input from a user so that information based on the input from the user is input to at least one of the first input unit, the learning module, and the output unit, and information output from the output unit varies based on the input from the user.

Abstract: A system that uses a learning module to realize execution of a predetermined task includes: a first input unit configured to receive information acquired from one or more external systems, and generate at least a portion of information to be input to the learning module; an output unit configured to acquire information output from the learning module, and generate information to be output from the system, the information output from the system being information based on which execution of a predetermined task is to be realized; and a second input unit configured to receive an input from a user so that information based on the input from the user is input to at least one of the first input unit, the learning module, and the output unit, and information output from the output unit varies based on the input from the user.

Abstract: A hypothesis testing position detection apparatus improves robustness against abnormal detection values, and achieves both high accuracy estimation and high-speed estimation processing. An image processing apparatus extracts, from calculated values for a central position of a plane shape, one of the calculated values nearer a provisional center as a candidate for evaluation (testing) performed using a plurality of detection points.

Abstract: An image inspection method executed by an image inspection apparatus includes an acquisition step of acquiring an inspection target object image obtained by capturing an image of an inspection target object, a setting reading step of reading, from a storage device that stores inspection region defining information in advance, the inspection region defining information, an inspection region extraction step of extracting, as an inspection region image, a portion to be an inspection region from the inspection target object image, based on the inspection region defining information, and an inspection processing step of performing inspection on the inspection target object by analyzing the inspection region image. The inspection region defining information comprises information defining an initial contour of the inspection region and information defining a range based on the initial contour as a search range for searching a contour of the inspection region.

Abstract: A method for displaying a result of area extraction processing of dividing a target image into a foreground area and a background area includes a result acquisition step of acquiring a result of the area extraction processing on the target image, an extraction result image generation step of acquiring an extraction result image representing an estimated foreground area or an estimated background area estimated by the area extraction processing or a boundary between the estimated foreground area and the estimated background area, based on the acquired result, and a display step of generating a composite image by combining the extraction result image with the target image, and displaying the composite image on a display device. The extraction result image generation step includes a color extraction step and a color determination step.

Abstract: An area partitioning method for partitioning an image into a foreground and a background includes a foreground designation step of causing a user to designate a part of pixels in an area that should be the foreground in the image as a foreground designating pixel, an estimation step of estimating a foreground color distribution and a background color distribution based on a color of the foreground designating pixel designated by the user, and an area partition step of partitioning the image into a foreground area and a background area with the estimated foreground color distribution and the estimated background color distribution as a condition. The estimation step includes dividing the color distribution of the image into a plurality of clusters, and selecting at least one cluster having a large relationship with the foreground designating pixel designated by the user in the plurality of clusters as the foreground color distribution.

Abstract: A hypothesis testing position detection apparatus improves robustness against abnormal detection values, and achieves both high accuracy estimation and high-speed estimation processing. An image processing apparatus extracts, from calculated values for a central position of a plane shape, one of the calculated values nearer a provisional center as a candidate for evaluation (testing) performed using a plurality of detection points.

Abstract: An image examination method includes an acquisition step of acquiring a to-be-examined object image obtained by capturing an image of a to-be-examined object, a setting reading step of reading an examination region definition information from a storage device in which the examination region definition information is previously stored, an examination region extracting step of extracting a portion constituting the examination region as an examination region image from the to-be-examined object image based on the examination region definition information, and an examination process step of examining the to-be-examined object by analyzing the examination region image. The examination region definition information is a parameter used as a constraint condition in an optimum solution search process.

Abstract: When there is a possibility that a third character region is redundantly selected in both a case where the line extraction process is performed starting from a first character region and a case where the line extraction process is performed starting from a second character region located in a line different from a line containing the first character region, the line recognition unit determines which line to incorporate the third character region in, by comparing a case of incorporating the third character region into the line starting with the first character region, with a case of incorporating the third character region into the line starting with the second character region.

Abstract: Disclosed is an image processing device that includes: a storage unit that holds model information including information indicating a plurality of feature points of a detection object; a correspondence-relationship determination unit that extracts a plurality of feature points included in an input image as a two-dimensional image or a three-dimensional image and that determines a correspondence relationship between an extracted plurality of feature points and a plurality of feature points of the model information; and a position estimating unit that estimates, based on the correspondence relationship, one or a plurality of second positions of the input image corresponding to one or a plurality of first positions set relatively to the detection object. The one or plurality of first positions is included in a point, a line, or a region.

Abstract: The invention provides an image processing device, an image processing method, and an image processing program capable of correctly discriminating a type of a test object, even when similar model images have been registered. The image processing device includes: a hardware that holds a feature amount obtained from model images of a plurality of reference objects belonging to mutually different types; a region determination module that determines a non-common region as a region indicating a feature amount different from those of other objects, within a model image of each object; and a discrimination module that discriminates which type an object included in an input image belongs to, by using a feature amount corresponding to a non-common region of the object out of feature amounts of objects.

Abstract: The invention provides an image processing device, an image processing method, and an image processing program capable of maintaining estimation accuracy even when an input image of a processing target includes a plurality of shape elements. The image processing device includes: a recognizing unit that recognizes one or more shape elements which are included in the input image from a feature amount included in the input image; a selecting unit that selects a desired shape element out of the recognized one or more shape elements; and an estimating unit that estimates a target shape element from information of a region corresponding to the selected shape element.

Abstract: The invention provides the image processing device that can shorten a time required for setting a parameter. The invention provides the image processing device that searches an input image for a feature amount based on a feature amount included in a model image. The image processing device includes: the hardware for holding a feature amount of a feature portion of the model image; the search-range reception module for receiving a setting value indicating a size of a range of searching the input image for a feature amount corresponding to the feature amount of the model image; the search-range determination module for determining, by using the setting value, a range of searching the input image for a feature amount corresponding to a feature amount of the model image; and the display module, in superposition with the model image, a search range determined by the search-range determination module.

Abstract: An area partitioning method for partitioning an image into a foreground and a background includes a foreground designation step of causing a user to designate a part of pixels in an area that should be the foreground in the image as a foreground designating pixel, an estimation step of estimating a foreground color distribution and a background color distribution based on a color of the foreground designating pixel designated by the user, and an area partition step of partitioning the image into a foreground area and a background area with the estimated foreground color distribution and the estimated background color distribution as a condition. The estimation step includes dividing the color distribution of the image into a plurality of clusters, and selecting at least one cluster having a large relationship with the foreground designating pixel designated by the user in the plurality of clusters as the foreground color distribution.

Abstract: When there is a possibility that a third character region is redundantly selected in both a case where the line extraction process is performed starting from a first character region and a case where the line extraction process is performed starting from a second character region located in a line different from a line containing the first character region, the line recognition unit determines which line to incorporate the third character region in, by comparing a case of incorporating the third character region into the line starting with the first character region, with a case of incorporating the third character region into the line starting with the second character region.

Abstract: An inspection area setting method for setting inspection area-defining information defining an inspection area to an image inspecting device, the image inspecting device being configured to extract a portion constituting the inspection area as an inspection area image from an original image obtained by taking an image of an inspection object, and to inspect the inspection object by analyzing the inspection area image, includes an acquisition step of acquiring a sample image obtained by taking an image of a sample of the inspection object, an inspection area searching step, and a setting step.

Abstract: An image processing method for identifying a region in an input image by character recognition, the region coinciding with a predetermined search condition, includes receiving the search condition, the search condition including assignments of plural format character strings, each format character string including an assignment of a character type or a specific character for each character of a recognition target, extracting a character string region becoming a candidate from the input image, calculating a similarity between a character recognition result and the plural format character strings with respect to each group of plural character string regions, the character recognition result being of each character string region included in each group, and determining the group coinciding with the search condition among the groups of plural character string regions according to the calculated similarity.

Abstract: Disclosed is an image processing device that includes: a storage unit that holds model information including information indicating a plurality of feature points of a detection object; a correspondence-relationship determination unit that extracts a plurality of feature points included in an input image as a two-dimensional image or a three-dimensional image and that determines a correspondence relationship between an extracted plurality of feature points and a plurality of feature points of the model information; and a position estimating unit that estimates, based on the correspondence relationship, one or a plurality of second positions of the input image corresponding to one or a plurality of first positions set relatively to the detection object. The one or plurality of first positions is included in a point, a line, or a region.

Abstract: The invention provides the image processing device that can shorten a time required for setting a parameter. The invention provides the image processing device that searches an input image for a feature amount based on a feature amount included in a model image. The image processing device includes: the hardware for holding a feature amount of a feature portion of the model image; the search-range reception module for receiving a setting value indicating a size of a range of searching the input image for a feature amount corresponding to the feature amount of the model image; the search-range determination module for determining, by using the setting value, a range of searching the input image for a feature amount corresponding to a feature amount of the model image; and the display module, in superposition with the model image, a search range determined by the search-range determination module.

Abstract: The invention provides an image processing device, an image processing method, and an image processing program capable of correctly discriminating a type of a test object, even when similar model images have been registered. The image processing device includes: a hardware that holds a feature amount obtained from model images of a plurality of reference objects belonging to mutually different types; a region determination module that determines a non-common region as a region indicating a feature amount different from those of other objects, within a model image of each object; and a discrimination module that discriminates which type an object included in an input image belongs to, by using a feature amount corresponding to a non-common region of the object out of feature amounts of objects.