Image processing apparatus
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.
1. An image processing apparatus that compares a target image and a reference image and thereby detects an anomaly in the target image, comprising
an anomaly detecting unit 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, wherein the filter process uses an object characteristic as a criteria; (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, wherein the anomaly detecting unit will determine a similarity ratio between the object in the first characteristic map and the object in the second characteristic map and exclude an object with the similarity ratio less than a predetermined threshold value when deriving the correction amount and (c) correct the target image 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.
2. The image processing apparatus according to claim 1 , wherein the anomaly detecting unit generates plural first characteristic maps and plural second characteristic maps obtained by performing filter processes corresponding to plural object types, derives a deviation between an object in the first characteristic map and an object in the second characteristic map for each of the object types, and derives the correction amount on the basis of the deviation.
3. The image processing apparatus according to claim 2 , wherein the anomaly detecting unit (a) corrects the target image or the reference image with the correction amount for each of the plural object types and thereafter generates difference images between the first characteristic maps and the second characteristic maps of the object types, and (b) detects an anomaly in the target image on the basis of the difference images of the object types.
4. The image processing apparatus according to claim 1 , wherein the anomaly detecting unit determines a cause of the detected anomaly on the basis of a characteristic amount of the detected anomaly.