Abstract: An image classifier receives input images and assigns each input image to one of a plurality of image classes. The image classifier includes plural class distribution maps, each based on a plurality of features evaluated on training images, and each representing those feature values that occur at least once among the training images belonging to the corresponding class. The image classifier further includes means for constructing a test map by evaluating the plurality of features on the input image. The image classifier further includes means for comparing the test map to the class distribution maps in order to identify which one of the class distribution maps has the least distance to the test map. At least one of the features is defined according to a rule that relates to the shapes of images of at least one image class. One advantageous method for evaluating features is carried out storing the input pattern, in a digital memory, as a point in a representational space.

Abstract: An image classifier, which performs character recognition, receives input images and assigns each input image to one of a plurality of image classes. The image classifier includes plural class distribution maps, each based on a plurality of features evaluated on training images, and each representing those feature values that occur at least once among the training images belonging to the corresponding class. The image classifier further includes means for constructing a test map by evaluating the plurality of features on the input image. The image classifier further includes means for comparing the test map to the class distribution maps in order to identify which one of the class distribution maps has the least distance to the test map. At least one of the features is defined according to a rule that relates to the shapes of images of at least one image class.

Abstract: Apparatus and methods for generating a set of defective images from a model image. Defect parameters used with the apparatus and methods specify classes of defects including resolution, blur, threshold, speckle, jitter, skew, distortion of width and height, offset from a baseline, and kerning. The parameters further permit specification of a range of sizes of the defects and a distribution of the defects within the range. Within the apparatus, actual values for the defects are generated randomly within the specified ranges and distributions. The model image may be represented by means of pixels or by a format which describes the model image's shape. The user may specify the number and the size of the defective images. The defective images are useful for inferring accurate and efficient image classifiers for use in image recognition devices such as optical character readers.

Abstract: Apparatus and methods for producing segmentations of images which contain text. The general approach is to locate a first set of components which contain text characters, locate a second set of components which do not contain text characters, sort the second set using a characteristic shape, make a cover set from the sorted second set, and use the cover set to locate the portions of the image which contain text. An example application where the present method may be applied is to texts employing the Manhattan layout to locate columns of text. Parts of the image which do not contain text are located by constructing maximum empty rectangles which do not contain characters. Based on the observation that columns in Manhattan layouts are separated by rectangles with a high aspect ratio, the maximum empty rectangles are sorted in a manner which favors such rectangles to produce the cover set.