High-order directional features and sparse representation based classification for in-air handwritten Chinese character recognition

A new hybrid-parameter recurrent neural network for online handwritten chinese character recognition

“…From Table 5, we can see the ensemble classifier can achieve the recognition accuracy of 93.7%. The proposed classifiers outperform the state-of-theart results (Qu et al 2016;Ren et al 2017).…”

“…This paper presents an end-to-end recognizer for online inair handwritten Chinese characters by using recurrent neural networks (RNN) and it has obtained competitive performance compared with the state-of-the-art methods (Ren et al 2017;Qu et al 2016). The merit of the proposed method is that it does not need the explicit feature representation in modeling the classifier.…”

“…Since the accuracy in (Qu et al 2016) is obtained only for the 3811 Chinese character classes, the experimental results in Table 4 are also reported on the 3811 Chinese characters for the sake of fair comparison. From Table 5, we can see the ensemble classifier can achieve the recognition accuracy of 93.7%.…”

“…and their system achieved a relatively low accuracy. Qu et al (Qu et al 2016) presented a new feature representation to extend the power of 8-direction feature and applied it in IAHCC recognition. 8-direction-feature had been shown to be a discriminative feature in many works and achieved a good performance (Bai and Huo 2005;Liu et al 2013;Jin et al 2010).…”

“…Comparison of recognition accuracy between ours and the state-of-the-art method(Qu et al 2016) Method Ours Ensemble Method#1. Method#2.…”