V. Govindaraju et Rk. Krishnamurthy, HOLISTIC HANDWRITTEN WORD RECOGNITION USING TEMPORAL FEATURES DERIVEDFROM OFF-LINE IMAGES, Pattern recognition letters, 17(5), 1996, pp. 537-540
Citations number
9
Categorie Soggetti
Computer Sciences, Special Topics","Computer Science Artificial Intelligence
This paper describes an algorithm for holistic recognition of off-line
cursive words using temporal stroke information derived from off-line
script. Temporal information is extracted by traversing the strokes w
ithout explicit segmentation of the word into constituent characters.
The word image is then mapped on to a feature vector matrix of uptrend
s and downtrends of strokes. This feature vector matrix is compared to
prestored feature vector of lexicon entries and ranked accordingly. O
n a test set of images, the temporal feature extraction rate is 80%. G
iven the correct set of temporal features, the recognition rate of the
holistic classifier is 81% on small lexicons.