00000ctmaa22000003a 4500 UP-1685675941123923468 Buklod 20151103151004.0 aa rb |||1 u| ta 151103s xx d r |||| u| (iLib)UPTAC-00017804978 UPVTC eng LG 993.5 2007 C66 C35 Calamay, Kenneth Lindsey T. author. CRUGA character recognition using Genetic Algorithm Kenneth Lindsey T. Calamay [and] Laurence Anthony B. Quejeda; John Paul T. Yusiong, adviser. 2007. [4], 32 leaves illustrations. Undergraduate thesis (B.S. Computer Science) -- University of the Philippines, Tacloban. Character Recognition in an automated or semi-automated manner has many applications in numerous fields. It is somehow quite impossible to create an algorithm that perfectly recognizes characters because of noise and varying font styles, therefore designing such algorithms with these failures in mind is important so that when mistakes are inevitably made, they will be understandable to the person working with the program. Generally, for more complex recognition problems Artificial Neural Networks (ANNs) are commonly used. An ANN is configured for a specific application, such as pattern recognition or data classification, through a learning process (i.e. training). NNs using BackPropagation (BP) perform well when applied to character recognition. However, a relatively newer technique-- Genetic Algorithms (GAs) due to its tendency to find the optimal solution seem to be a better training algorithm. Experiments have shown that genetic algorithm is better than backpropagation at finding solutions but at the expense of time and resources. Character recognition. Genetic Algorithms. Neural networks. OCR. Training algorithms. Quejada, Laurence Anthony B. author. Yusiong, John Paul T. adviser. FI UP UPTAC UPTAC LG 993.5 2007 C66 C35 Thesis