| 摘要 |
In one or more embodiments described herein, there is provided a method of training an apparatus. The method trains the apparatus to automatically detect features of interest in an image. An image is received, the image being of at least one object for inspection, each image comprising a plurality of pixels. The image is segmented into a plurality of superpixels, each superpixel comprising a plurality of pixels which each have similar image data attributes to one another. The superpixels are classified into at least two classes in response to user input identifying at least one feature of interest in one or more of the super-pixels. From a library of image data attributes, a subset of image data attributes is determined that provides preferential discrimination between the at least two classes. The apparatus is then trained using said determined subset of image data attributes to thereby enable the apparatus to classify super-pixels of an image into the at least two classes. |
