Abstract: Machine vision inspection methods and systems according to the invention take an average (or other statistical measure) of pixel values within neighborhoods or groups of pixels within an image. The averages are compared with one or more thresholds and a result generated for each neighborhood. The results generated for all such neighborhoods can, for example, be used to identify defective regions in the acquired image, notwithstanding a high degree of intensity, brightness, color or contrast variation at the pixel level—e.g., of the type commonly occurring when imaging non-woven materials. Such methods and systems are advantageous because an originally acquired, high-resolution (non-defocused) image can be preserved and processed in parallel with a neighborhood-based defocused and thresholded image. Systems employing these methods achieve the thresholding capability of traditional defocused systems, while providing clear, detailed, high-resolution images for display or other analysis.

Abstract: An improved classification system for classifying characteristics of an article into classes of characteristics based on features associated with the characteristics. The system includes a first rule-based classifier that provides rules that embody requirements of selected features so as to together define selected classes. These rules are applied to measured features of an article characteristic to assign one of the selected classes to that characteristic, should the article characteristic meet the feature requirements of one of the selected classes. The system also includes a trainable classifier configured based on a training set of preclassified characteristics, with the trainable classifier connected so as to accept from the first rule-based classifier an article characteristic not classified by the rule based classifier.