Whole Word Handwritten Numerals Recognition Using Word-Pattern Statistics

摘要

Two methods for recognizing hand written bank check numerals is proposed. Both of the methods are developed on the basis of simple global feature to achieve possible efficient result in both feature extraction and pattern recognition phases. In the first method, the feature extraction was recorded by using polynomial equation to estimate the strokes in word sections. The second method extracted features by mapping gradient values to two dimensional gradient space planes. The recognition process was based on the mean value and standard deviations of extracted feature. The lexicon with closest mean value and smallest Euclidean value to the test samples were output as the recognition result. After simple preprocessing of the current sample, initial test shows both methods have promising potential in handwriting extraction. Polynomial function estimation has better expression than GS method in lexicon recognition with ascender and descenders. The average recognition rate for PL and GS methods are 63% and 57% respectively in current experimental level.