IMAGE CLASSIFICATION METHOD AND IMAGE CLASSIFICATION APPARATUS

摘要

In an apparatus for automatically classifying an image taken of a defect on a semiconductor wafer according to user defined class, when images taken by a plurality of different observation apparatuses are input in a mixed manner, the defect image classification accuracy rate decreases due to image property differences corresponding to differences in the observation apparatuses. Provided is an automatic image classification apparatus supplied with defect images taken by a plurality of observation apparatuses, in which, when preparing a recipe, image process parameters are adjusted and a class identification plane is prepared for each observation apparatus. When classifying an image, the observation apparatus that took a defect image is identified on the basis of accompanying information or the like of the image, and an image process and a classification process are performed by using the image process parameters and the class identification plane corresponding to the observation apparatus that took the image. In order to efficiently adjust the image process parameters for each observation apparatus, appropriate image process parameters are automatically adjusted on the basis of a taught defect area. The image process parameters adjusted in a given observation apparatus may be used for setting the image process parameters for another observation apparatus.