Dynamic Programming Matching with Global Features for Online Character Recognition

Abstract

Abstract-This paper proposes a dynamic programming (DP) matching method with global features for online character recognition. Many online character recognition methods have utilized the ability of DP matching on compensating temporal fluctuation. On the other hand, DP requires the Markovian property on its matching process. Consequently, most traditional DP matching methods have utilized local information of strokes such as xy-coordinates or local directions as features, because it is easy to satisfy the Markovian property with those features. Unfortunately, these local features cannot represent global structure of character shapes. Although global features that extract global structures of characters have high potential to represent various key characteristics of character shapes, conventional DP matching methods cannot handle global features. This is because the incorporation of global features is not straightforward due to the Markovian property of DP. In this paper we propose a new scheme for DP matching using global features. Our method first selects global features which not only satisfy the Markovian property but also have sufficient discrimination ability. By embedding the selected global features into DP matching process, we can compensate temporal fluctuation while considering the global structure of the pattern. Experimental results show that our methods can enhance the recognition accuracy for online numeral characters.

Self-Learning Based Cognitive Reading and Character Recognition in Image Processing Techniques

“…They evaluated on different scripts like Latin, Chinese, Greek, Cyrillic, Japanese, Farsi and Sanskrit language-based text where input samples are evaluated using Gaussian mixture model commonly called as GMM classifier [10] and it attempts to evaluate the model of each feature class in combination of Gaussian model distribution. In this method, a wavelet log based on co-occurrence of feature based on texture using script classification where a overall error rate is logged as 1% error [11].…”