As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
This paper presents a recognition system for handwritten character that utilized the chain code and the image properties features as image representation. Thinning algorithm was applied first to the original image to produced thinned binary image before extracting the chain code. Then, chain code feature was extracted by metaheuristic feature extraction algorithm. Once the chain code has been extracted, a feature vector was derived based on the chain code and the image properties. The derivation of feature vector is based on the formation rule in terms of Local Value Formation Rule (LVFR) and Global Value Formation Rule (GVFR). After that, a back propagation neural network was used as a classification model to classify the image character based on the generated feature vectors. National Institute of Standards and Technology (NIST) handwritten character database were applied in the experiment. Finally, the performance of the classification models was measured in terms of precision, sensitivity, specificity, F-score and accuracy.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.