Abstract: An abnormality detection unit detects an abnormal object in target images repeatedly acquired. An abnormality type selection unit selects, for each of the target images, an abnormality type of the abnormal object from a plurality of specific abnormality types based on values of at least two basic feature amounts. A feature amount monitoring unit monitors the values of the basic feature amounts and a value of an auxiliary feature amount corresponding to the abnormality type currently selected by the abnormality type selection unit. An adjustment processing unit executes an adjustment process corresponding to the auxiliary feature amount being monitored by the feature amount monitoring unit. The abnormality type selection unit changes the abnormality type to be selected, in accordance with the change in the values of the basic feature amounts mentioned above.

Abstract: A feature-amount extraction unit generates a base feature-map group constituted by a plurality of base feature maps from an input image, applies a plurality of statistic calculations to the base feature maps in the base feature-map group, and generates a plurality of types of statistic maps. The inference unit derives inference results of segmentation for inference inputs based on the plurality of statistic maps. Each of the plurality of types of statistic calculations described above is processing of calculating a statistic with a specific window size and a specific calculation formula, and the plurality of types of statistic calculations are different from each other in at least either one of the window size and the calculation formula.

Abstract: An anomaly detecting unit detects an anomaly object in a target image. A characteristic amount watching unit watches at least two basic characteristic amounts of the anomaly object, determines whether values of the basic characteristic amounts satisfy a predetermined watching determination condition of any one of predetermined plural anomaly types or not, if it is determined that the values of the basic characteristic amounts satisfy the watching determination condition, determines as an auxiliary characteristic amount for the anomaly object a characteristic amount corresponding to the anomaly type of which the values of the basic characteristic amounts satisfy the watching determination condition, and starts watching a value of the auxiliary characteristic amount. An anomaly type determining unit determines an anomaly type of the anomaly object on the basis of the basic characteristic amounts and the auxiliary characteristic amount currently watched by the characteristic amount watching unit.

Abstract: An image processing apparatus compares a target image and a reference image and thereby detects an anomaly in the target image, and includes an anomaly detecting unit. The anomaly detecting unit is configured to (a) generate a first characteristic map obtained by performing a filter process for the target image and a second characteristic map obtained by performing the filter process for the reference image, (b) derive a correction amount on the basis of a deviation between an object in the first characteristic map and an object in the second characteristic map, and (c) correct the target image and/or the reference image with the correction amount and thereafter compare the target image and the reference image and thereby detect an anomaly in the target image.

Abstract: An image recognition method includes a feature amount extracting step of generating, from an input image, a base feature map group including a plurality of base feature maps; an inferring step of deriving a plurality of inference results using each of a plurality of machine-learned inference devices for a plurality of inference inputs based on the base feature map group; and an integrating step of integrating the plurality of inference results by a specific manner to derive a final inference result, where each of the plurality of inference inputs has some or all base feature maps of the plurality of base feature maps, and each of the plurality of inference inputs has the some or all base feature maps that are different in part or whole from the some or all base feature maps of another inference input in the plurality of inference inputs.