Preliminary Design and Application Prospect of Single Chinese Character Calligraphy Image Scoring Algorithm

This paper improves the image classification task based on deep learning and proposes a new font grading system to help calligraphy lovers to practice calligraphy. The basic model of the framework proposed in this paper is ResNet, and then dilated convolution, deformable convolutional, and deformable pooling are used on the traditional ResNet to improve performance. Experimental results show that the proposed algorithm can make a reasonable judgment on handwriting.

[1]  Yi Li,et al.  Deformable Convolutional Networks , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[2]  Giorgio Metta,et al.  Keep it simple and sparse: real-time action recognition , 2013, J. Mach. Learn. Res..

[3]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[5]  Qi Wang,et al.  Hyperspectral Image Classification via Multitask Joint Sparse Representation and Stepwise MRF Optimization , 2016, IEEE Transactions on Cybernetics.

[6]  Cewu Lu,et al.  Two-Class Weather Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Maria Bernathova,et al.  A simple classification system (the Tree flowchart) for breast MRI can reduce the number of unnecessary biopsies in MRI-only lesions , 2017, European Radiology.

[8]  Mark D Cicero,et al.  Training and Validating a Deep Convolutional Neural Network for Computer-Aided Detection and Classification of Abnormalities on Frontal Chest Radiographs , 2017, Investigative radiology.