Effectiveness of Feature and Classifier Algorithms in Character RecognitionSystems

摘要

At the first Census Optical Character Recognition (OCR) Systems Conference, NISTgenerated accuracy data for more than 40 character recognition systems. Most systems were tested on the recognition of isolated digits and upper and lower case alphabetic characters. The recognition experiments were performed on sample sizes of 58,000 digits, and 12,000 upper and lower case alphabetic characters. The algorithms used by the 26 conference participants included rule-based methods, image-based methods, statistical methods, and neural networks. The neural network methods included Multi-Layer Perceptrons, Learned Vector Quantitization, Neocognitrons, and cascaded neural networks. In this paper, 11 different systems are compared using correlations between the answers of different systems, comparing the decrease in error rate as a function of confidence of recognition. This comparison shows that methods that used different algorithms for feature extraction and recognition performed with very high levels of correlation. This is true for neural network systems, hybrid systems, and statistically based systems, and leads to the conclusion that neural networks have not yet demonstrated a clear superiority to more conventional statistical methods.