We report on results of training backpropagation nets with samples of hand-printed digits scanned off of bank checks and hand-printed letters interactively entered into a computer through a stylus digitizer. Generalization results are reported as a function of training set size and network capacity. Given a large training set, and a net with sufficient capacity to achieve high performance on the training set, nets typically achieved error rates of 4-5% at a 0% reject rate and 1-2% at a 10% reject rate. The topology and capacity of the system, as measured by the number of connections in the net, have surprisingly little effect on generalization. For those developing hand-printed character recognition systems, these results suggest that a large and representative training sample may be the single, most important factor in achieving high recognition accuracy. Benefits of reducing the number of net connections, other than improving generalization, are discussed.Practical interest in hand-printed character recognition is fueled by two current technology trends: one toward systems that interpret hand-printing on hard-copy documents and one toward notebook-like computers that replace the keyboard with a stylus digitizer. The stylus enables users to write and draw directly on a flat panel display. In this paper, we report on the results of applying multilayered neural nets trained through backpropagation (Rumelhart et al. 1986) to both cases.Developing hand-printed character recognition systems is typically a two-stage process. First, intuition and lengthy experimentation are used to select a set of features to represent the raw input pattern. Then a variety of techniques are used to optimize the classifier system that assumes this featural representation. Most applications of backpropagation learning to character recognition use the learning capabilities only for this latter stagedeveloping the classifier system (Burr 1986; Denker ef al. 1989;Mori and Yokosawa 1989; Weideman rf al. 1989).We have come to believe that the strength of backpropagation techniques in this domain lies in automating the development process. We find that much of the hand-crafting involved in selecting features can be Neural Cnmprctaatiari 3, 258-267 (1991) @ 1YY1 Massachusetts Institute of Technology
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.