Abstract: An abnormality detecting system for detecting an abnormality of an animal that is a monitoring target is provided. The abnormality detecting system includes a inferring unit configured to infer on a per-predeterinined-time-period basis whether a ruminating action of an animal that is a monitoring target occurs, by inputting time-series data from a motion sensor placed on a predetermined portion of the animal into a time-series model; and a determining unit configured to calculate a rumination rate that is a rate at which the inferring unit infers that the ruminating action occurs, and, in response to the rumination rate satisfying a predetermined condition, determine that an abnormality of the animal is detected.

Abstract: An abnormality detecting system includes a first identification unit configured to identify a state of an animal that is a monitoring target in each time range, based on time-series data from a motion sensor placed on a predetermined portion of the animal that is a monitoring target; a first calculation unit configured to calculate a transition probability from the state at a predetermined timing of each time range identified by the first identification unit to a next state; and a determining unit configured to determine that an abnormality of the animal that is a monitoring target is detected when a score calculated based on the transition probability to the next state satisfies a predetermined condition.

Abstract: Provided is an image classification system for classifying an input image including: a network constructed so that feature amount extraction processing and fully connected processing are executed on input image data; a path extracting means configured to extract a processing path in the network; and a determination module configured to compare the processing path extracted by the path extracting means and a plurality of setting paths set in advance in association with classes to set a class associated with a matched path as a class of the input image.

Abstract: A class determination system includes a memory and a processor to execute classifying image data of an object to be inspected into one of a predetermined number of classes; extracting, in association with a classification target, a feature value by processing the image data classified by the classifying; determining whether the feature value of the image data of the object is included in a distribution region of the classification target into which the image data of the object is classified, from among distribution regions of feature values of image data items whose classification targets are known, where in each distribution region, a feature value space is defined for a corresponding classification target; and outputting, when the feature value of the image data of the object is determined not included in the distribution region, a determination result that the image data of the object belongs to a new class.

Abstract: An inspection system includes a memory; and a processor, wherein the memory is configured to hold an image reproducing model trained to reproduce, from a first masked image generated by masking part, of a first image determined as including no defect from among images that capture an object to be inspected, the first image before being masked, and wherein the processor is configured to determine, based on a reproduced image reproduced by inputting a second masked image generated by masking part of a second image that captures a new object to be inspected into the image reproducing model, and the second image, whether the second image includes a defect.

Abstract: A BRDC sign detecting system includes: a processor, and a memory storing program instructions that cause the processor to obtain, with respect to a bovine developing bovine respiratory disease complex (BRDC) within a time period required for a fattening process, data indicating a condition of the bovine during a predetermined time period in which the bovine did not yet develop the BRDC, and obtain data indicating a condition, during a predetermined time period, of a bovine that has not developed BRDC perform machine learning with respect to a correspondence relation between the obtained data indicating the condition during the predetermined time period and information indicating whether BRDC is developed, and infer, by inputting data indicating a condition of a new bovine during the predetermined time period into a learned model generated by performing the machine learning, information indicating whether the new bovine will develop BRDC and output an inference result.

Abstract: An inspection apparatus configured to inspect a target for defects, including: an image capturing unit capable of capturing an image of the target as image information having color information including RGB values; and a determination unit configured to determine presence or absence of defects in the target based on the color information of the image information of the image captured by the image capturing unit, wherein the determination unit is configured to define, for each pixel, criteria for determining presence or absence of defects in each pixel of the image information, based on the color information in a defect-free region of the target captured by the image capturing unit, and to filter all pixels in the image information of the image captured by the image capturing unit so as to determine presence or absence of defects in each pixel, based on the defined criteria.

Abstract: Provided is an image classification system for classifying an input image including: a network constructed so that feature amount extraction processing and fully connected processing are executed on input image data; a path extracting means configured to extract a processing path in the network; and a determination module configured to compare the processing path extracted by the path extracting means and a plurality of setting paths set in advance in association with classes to set a class associated with a matched path as a class of the input image.

Abstract: An inspection apparatus configured to inspect a target for defects, including: an image capturing unit capable of capturing an image of the target as image information having color information including RGB values; and a determination unit configured to determine presence or absence of defects in the target based on the color information of the image information of the image captured by the image capturing unit, wherein the determination unit is configured to define, for each pixel, criteria for determining presence or absence of defects in each pixel of the image information, based on the color information in a defect-free region of the target captured by the image capturing unit, and to filter all pixels in the image information of the image captured by the image capturing unit so as to determine presence or absence of defects in each pixel, based on the defined criteria.