Feature Fusion And Decomposition: Exploring A New Way For Chinese Calligraphy Style Classification

Chinese calligraphy is an invaluable legacy of Chinese culture,since it bears great artistic and aesthetic value.In this paper,we aim at the problem of Chinese calligraphy style classification,which is an important branch of Chinese calligraphy study.Chinese calligraphy style classification remains a challenging task due to its dramatic intra-class difference and tiny inter-class difference.Therefore,we propose a novel CNN embedded with feature fusion and feature decomposition modules to solve this problem.We first fuse the features of several images from the same category to augment their potential style-related features.Then we feed the fused feature to an attention module to decompose it to two components,viz.style-related feature and styleunrelated feature.We further apply two types of loss function to jointly supervise our network.On one hand,we feed the style-related feature to a style classifier which is supervised by cross-entropy loss.On the other hand,we construct a correlation loss based on the Pearson correlation coefficient to make the two decomposed features as orthogonal as possible.We complete the network training through optimizing these two types of loss functions simultaneously.Since the capacity of existing datasets for Chinese calligraphy style classification are relatively small,we extended the existing dataset and performed some blurring to make the images closer to the real scene.We conducted substantial ablation study and comparison experiments on the existing CCS dataset and the newly created eCCS dataset.The ablation study validates the effectiveness of the feature fusion module and the feature decomposition module,and the proposed method compares favorably with state-of-the-art methods on both two datasets,obtain the accuracies of 98.63% and94.35% respectively.