Using constrained snakes for feature spotting in off-line cursive script

Studies in the psychology of reading indicate that reading probably involves recognising features which are present in letters, such as loops, turns and straight strokes. If this is the case it is likely that recognising these features will be a useful technique for the machine recognition of cursive script. This paper describes a new method of detecting the presence of these features in a cursive handwritten word. The method uses constrained snakes which adapt to t the maxima in the distance transform of a word image while retaining their basic shape. When the snake has settled into a potential minimum, its goodness-of-t is used to determine whether a match has been found. The features located by this method are passed on to a `neural' network recogniser. Examples of the features recognised are shown and results for word recognition for this method, on a single-author database of scanned data with 825 word vocabulary are presented. These are followed by a conclusion and pointers to further work.