This paper presents new upper and lower bounds on the minimum probability of error of Bayesian decision systems for the two-class problem. These bounds can be made arbitrarily close to the exact minimum probability of error, making them tighter than any previously known bounds.

Optical character recognition (OCR) refers to a process whereby printed documents are transformed into ASCII files for the purpose of compact storage, editing, fast retrieval, and other file manipulations through the use of a computer. The recognition stage of an OCR process is made difficult by added noise, image distortion, and the various character typefaces, sizes, and fonts that a document may have. In this study a neural network approach is introduced to perform high accuracy recognition on multi-size and multi-font characters; a novel centroid-dithering training process with a low noise-sensitivity normalization procedure is used to achieve high accuracy results. The study consists of two parts. The first part focuses on single size and single font characters, and a two-layered neural network is trained to recognize the full set of 94 ASCII character images in 12-pt Courier font. The second part trades accuracy for additional font and size capability, and a larger two-layered neural network is trained to recognize the full set of 94 ASCII character images for all point sizes from 8 to 32 and for 12 commonly used fonts. The performance of these two networks is evaluated based on a database of more than one million character images from the testing data set.>

This paper addresses a correlation based nearest neighbor pattern recognition problem where each class is given as a collection of subclass templates. The recognition is performed in two stages. In the first stage the class is determined. Templates for this stage are created using the subclass templates. Assignment into subclasses occurs in the second stage. This two stage approach may be used to accelerate template matching. In particular, the second stage may be omitted when only the class needs to be determined. The authors present a method for optimal aggregation of subclass templates into class templates. For each class, the new template is optimal in that it maximizes the worst case (i.e. minimum) correlation with its subclass templates. An algorithm which solves this maximin optimization problem is presented and its correctness is proved. In addition, test results are provided, indicating that the algorithm's execution time is polynomial in the number of subclass templates. The authors show tight bounds on the maximin correlation. The bounds are functions only of the number of original subclass templates and the minimum element in their correlation matrix. The algorithm is demonstrated on a multifont optical character recognition problem.>

This paper presents four lossless acceleration algorithms for a special type of nearest-neighbor pattern recognition whereby correlation functions are used. The algorithms are called template stopping, template ordering, pixel stopping, and pixel ordering. All four algorithms may be used either independently or simultaneously to accelerate the nearest-neighbor search without incurring any loss to accuracy. To illustrate their usefulness, all four algorithms are demonstrated on an optical character recognition system.