Chinese Font Recognition Based on Convolution Neural Network
暂无分享,去创建一个
In the traditional OCR text recognition system, recognition rate is low with many errors.Also, it can not effectively identify the different text fonts. It’s a long-standing problem. Modern text recognition system should be for different fonts within accuracy to identify the text and font information. The traditional methods are mostly based on feature extraction, including local features extraction and global features extraction. Proposes a Convolution Neural Network[1] based on deep learning to deal with Chinese font recognition. Compared with the previous methods, this method has high recognition rate and high speed and is suitable for complex applications.
[1] Geoffrey E. Hinton,et al. ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.
[2] Xing Xiang-hua. Method of Quickly Recognizing Vehicle Plate Based on Pattern Matching and Characteristic Dot Matching , 2003 .