期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：9003
DOI：10.15680/IJIRCCE.2017.05040354
出版社：S&S Publications
摘要：Character recognition is a process by which computer recognizes handwritten characters and turns theminto a format which a user can understand. Computer based pattern recognition is a process that involves several subprocesses.In today’s environment character recognition has gained lot of concentration in the field of patternrecognition. Handwritten character recognition is useful in cheque processing in banks, form processing systems andmany more. Character recognition is one of the well-liked and challenging area of research. In future, characterrecognition creates paperless environment. The novelty of this approach is to achieve better accuracy, reducedcomputational time for recognition of handwritten characters. The proposed method extracts the geometric features ofthe character contour. These features are based on the basic line types that forms the character skeleton. The systemgives a feature vector as its output. The feature vectors so generated from a training set, were then used to train apattern recognition engine based on Neural Networks so that the system can be benchmarked. The algorithm proposedconcentrates on the same. It extracts different line types that forms a particular character. It also concentrates on thepositional features of the same. The feature extraction technique explained was tested using a Neural Network whichwas trained with the feature vectors obtained from the proposed method.
关键词：character recognition; character segmentation; feature extraction; preprocessing; neural network.
