Abstract: A learning method of a value calculation model for calculating a value of an option used when a person acts from an attribute value of the option, includes acquiring input data in which a selection probability indicating a rate at which each option is selected from a plurality of options and attribute values of the plurality of options when the selection probability is obtained are associated with each other, and acquiring, for each combination of two options that can be extracted from the plurality of options, a relationship between selection probabilities of the two options included in each combination from the input data, and adjusting the value calculation model so that a relationship between values calculated when attribute values of the two options included in each combination are input to the value calculation model and a relationship between the selection probabilities corresponding to each combination are close to each other.

Abstract: A detection apparatus includes a memory and a processor coupled to the memory. The processor configured to determine a position of each of a plurality of partial images relative to the wide-angle image, to extract, from among the plurality of partial images, a pair of partial images that are consecutive in an image-capturing order, that do not have an overlapping portion, and at least one of which includes an image of a damaged portion, to detect a region of the outside of the partial image to which a damaged portion is estimated to be continuous, as an image-capturing omission candidate region, to determine the image-capturing omission candidate region as an image-capturing omission region, in a case where the image-capturing omission candidate region is included in none of the other partial images, and to issue, based on the position, a notification of a position corresponding to the image-capturing omission region.

Abstract: An information processing apparatus includes: a processor configured to: partition an image of a structure into regions; detect, for target regions each including crack points among the regions, a representative line segment representing the crack points included in each target region as a basic line segment for each target region; generate, based on basic line segments whose end points are close to each other among the detected basic line segments, a tree structure having an end point of a specific basic line segment as a root; and detect, among routes in the generated tree structure, routes from a top to a bottom of the tree structure corresponding to a basic line segment group in which values indicating degrees of coupling probability between the basic line segments are highest and a total length of the basic line segments coupled is longest, as a stroke corresponding to crack lines.

Abstract: A detection apparatus includes a memory and a processor coupled to the memory. The processor configured to determine a position of each of a plurality of partial images relative to the wide-angle image, to extract, from among the plurality of partial images, a pair of partial images that are consecutive in an image-capturing order, that do not have an overlapping portion, and at least one of which includes an image of a damaged portion, to detect a region of the outside of the partial image to which a damaged portion is estimated to be continuous, as an image-capturing omission candidate region, to determine the image-capturing omission candidate region as an image-capturing omission region, in a case where the image-capturing omission candidate region is included in none of the other partial images, and to issue, based on the position, a notification of a position corresponding to the image-capturing omission region.

Abstract: An image processing apparatus includes a memory and a processor coupled to the memory. The processor is configured to classify each of a plurality of images into one of a plurality of groups based on a feature of each of the plurality of images. The processor is configured to store first information in the memory. A first recognition method is associated with a first group in the first information and images classified into the first group are correctly recognized by the first recognition method. The processor is configured to store second information in the memory. One of at least one second recognition method different from the first recognition method is associated with a second group in the second information and images classified into the second group are incorrectly recognized by the first recognition method.

Abstract: An apparatus includes a memory configured to store training data used for automatically sorting objects. The apparatus acquires a first captured-image that is captured at a first timing before an object-sorting work for sorting objects is performed, and a second captured-image that is captured at a second timing after the object-sorting work has been performed, and extracts, from each of the first captured-image and the second captured-image, a feature amount of an object-image that is an image of an object included in each of the first captured-image and the second captured-image. The apparatus stores, in the memory, as the training data, a first feature amount corresponding to a first object whose object-image is included in both the first captured image and the second captured image, or a second feature amount corresponding to a second object whose object-image is included in only one of the first captured-image and the second captured-image.

Abstract: An information processing apparatus includes: a processor configured to: partition an image of a structure into regions; detect, for target regions each including crack points among the regions, a representative line segment representing the crack points included in each target region as a basic line segment for each target region; generate, based on basic line segments whose end points are close to each other among the detected basic line segments, a tree structure having an end point of a specific basic line segment as a root; and detect, among routes in the generated tree structure, routes from a top to a bottom of the tree structure corresponding to a basic line segment group in which values indicating degrees of coupling probability between the basic line segments are highest and a total length of the basic line segments coupled is longest, as a stroke corresponding to crack lines.

Abstract: A non-transitory computer-readable storage medium having stored therein a program for verifying content, the program executing a process includes identifying, among a plurality of elements included in a content to be verified and displayed in two browsers that display the content respectively, a dynamic element whose attribute relating to display changes over time or whose element image changes over time in at least one of the two browsers; and identifying an area in which displayed content is different between the two browsers by comparing element images of the plurality of elements other than the dynamic element between the two browsers.

Abstract: An image processing method is performed by a computer for estimating a width of a crack or the like. The method includes: extracting a linear region in which a linear damage appears from an image of an object captured by an imaging apparatus; calculating a luminance information sum by adding luminance information of each pixel included in the linear region in a direction crossing the linear region; and estimating, from the calculated luminance information sum, based on a relational expression indicating a relationship between luminance information sum and a width of a damage, a width of the linear damage.

Abstract: An image processing method causing an image processing device to execute a process including: obtaining a first image and a second image captured at different timings for an identical inspection target by passing through an imaging range of an image sensor row; extracting respective feature points of the first image and the second image; associating the feature points of the first image and the feature points of the second image with each other; estimating a conversion formula to convert the feature point of the second image to the feature point of the first image based on a restraint condition of a quadratic equation, in accordance with respective coordinates of three or more sets of the feature points associated between the first image and the second image; and converting the second image into a third image corresponding to the first image based on the estimated conversion formula.

Abstract: An image processing apparatus includes a memory and a processor coupled to the memory. The processor is configured to classify each of a plurality of images into one of a plurality of groups based on a feature of each of the plurality of images. The processor is configured to store first information in the memory. A first recognition method is associated with a first group in the first information and images classified into the first group are correctly recognized by the first recognition method. The processor is configured to store second information in the memory. One of at least one second recognition method different from the first recognition method is associated with a second group in the second information and images classified into the second group are incorrectly recognized by the first recognition method.

Abstract: An image processing method for tracking an object, the method includes: specifying a first range in which a first target is searched for and a second range in which a second target is searched for in a next frame by referring to a storage device that stores past frames captured by a capturing device; changing the first range and/or the second range in the next frame such that an area in which the first range and the second range specified in the next frame overlap each other is less than a predetermined value in a case where the overlapping area is equal to or greater than the predetermined value; and searching for, in the changed first range and the changed second range, and specifying a region corresponding to the first target and a region corresponding to the second target in the next frame.

Abstract: A method includes: extracting a first line segment pair including a combination of line segments selected from a plurality of line segments included in an image of a form to be recognized; calculating a first feature amount which represents a relationship between the line segments in the extracted first line segment pair; extracting a candidate for a form identifier of the form to be recognized based at least on the calculated first feature amount and a second feature amount in line segments in a second line segment pair correlated with a form identifier which is registered in advance; extracting corresponding line segment pairs which include a line segment correlated with the candidate for the form identifier and a line segment of the form to be recognized; and specifying the form identifier of the form to be recognized based at least on the degree of overlapping.

Abstract: An image processing method includes: identifying a dark region by binarizing an image captured using an imaging device; generating a line image of the dark region by thinning the dark region; identifying a first multiple pairs of pixels that are included in a pixel group forming the generated line image and are separated from each other by a predetermined threshold or more; calculating a first variance of gradients of lines connecting the respective pairs in the first plurality of pairs; identifying a second plurality of pairs of pixels that are included in the pixel group forming the generated line image and are separated from each other by values smaller than the predetermined threshold; calculating a second variance of gradients of lines connecting the respective pairs in the second plurality of pairs; and evaluating the dark region based on the first variance and the second variance.

Abstract: An apparatus includes a memory configured to store training data used for automatically sorting objects. The apparatus acquires a first captured-image that is captured at a first timing before an object-sorting work for sorting objects is performed, and a second captured-image that is captured at a second timing after the object-sorting work has been performed, and extracts, from each of the first captured-image and the second captured-image, a feature amount of an object-image that is an image of an object included in each of the first captured-image and the second captured-image. The apparatus stores, in the memory, as the training data, a first feature amount corresponding to a first object whose object-image is included in both the first captured image and the second captured image, or a second feature amount corresponding to a second object whose object-image is included in only one of the first captured-image and the second captured-image.

Abstract: A non-transitory computer-readable storage medium having stored therein a program for verifying content, the program executing a process includes identifying, among a plurality of elements included in a content to be verified and displayed in two browsers that display the content respectively, a dynamic element whose attribute relating to display changes over time or whose element image changes over time in at least one of the two browsers; and identifying an area in which displayed content is different between the two browsers by comparing element images of the plurality of elements other than the dynamic element between the two browsers.

Abstract: An image processing method causing an image processing device to execute a process including: obtaining a first image and a second image captured at different timings for an identical inspection target by passing through an imaging range of an image sensor row; extracting respective feature points of the first image and the second image; associating the feature points of the first image and the feature points of the second image with each other; estimating a conversion formula to convert the feature point of the second image to the feature point of the first image based on a restraint condition of a quadratic equation, in accordance with respective coordinates of three or more sets of the feature points associated between the first image and the second image; and converting the second image into a third image corresponding to the first image based on the estimated conversion formula.

Abstract: A non-transitory computer-readable storage medium storing an event detection program that causes a computer to perform a process, the process including acquiring a first captured image captured at a first timing by a first camera device, acquiring a second captured image captured at a second timing after the first timing by a second camera device, detecting an event in accordance with a first image feature extracted from the first captured image, a second image feature extracted from the second captured image and an event detection criteria, the event detection criteria making the event less detectable as a variance of the first image feature or a variance of the second image feature is smaller, both the first image feature and the second image feature corresponding to one or more target objects, and outputting a result of the detecting of the event.

Abstract: An image processing method includes: identifying a dark region by binarizing an image captured using an imaging device; generating a line image of the dark region by thinning the dark region; identifying a first multiple pairs of pixels that are included in a pixel group forming the generated line image and are separated from each other by a predetermined threshold or more; calculating a first variance of gradients of lines connecting the respective pairs in the first plurality of pairs; identifying a second plurality of pairs of pixels that are included in the pixel group forming the generated line image and are separated from each other by values smaller than the predetermined threshold; calculating a second variance of gradients of lines connecting the respective pairs in the second plurality of pairs; and evaluating the dark region based on the first variance and the second variance.

Abstract: A moving object group detection method includes: respectively analyzing a first captured image captured by a first image capture device and a second captured image captured by a second image capture device, and respectively extracting a first image region and a second image region from the first captured image and the second captured image, the first image region and the second image region being regions in which coloring patterns satisfy a predetermined similarity range and moving in corresponding directions over plural frames; and detecting that a common moving object group is included in the first image region and the second image region on the basis of an evaluation of similarity between an image within the first image region and an image within the second image region.