Small sample learning of calligraphy and painting identification based on hyperspectral image

The existence of forgeries has seriously affected the fair trading, protection and inheritance of calligraphy and painting, while, it been unable to identify high-level counterfeiting means by traditional expert eye identification method. Combining the advantages of material attribute recognition and imaging analysis of hyperspectral imaging technology with the powerful feature expression and classification ability of convolutional neural network, the identification level of calligraphy and painting could be improved. However, there are still some practical problems in the application, like the small sample learning problem caused by the difficulty in obtaining the real hyperspectral sample data of calligraphy and painting. In this paper, a 10-hidden layers 2D-CNN convolutional neural network transfer learning method for calligraphy and painting identification with data enhancement is proposed by using a large number of relevant picture data and a small amount of MNF dimensionality reduced hyperspectral data. The experimental test shows that on the test set of this paper, for the identification of calligraphy and painting authors and authenticity, the accuracy of migration learning with data enhancement under the original sample are separately 97.5% and 94.8%, the accuracy of migration learning with data enhancement under half of the original sample are separately 94.3% and 92.8%, which shows the migration learning and data enhancement is helpful, and the identification accuracy of half of the original sample basically reaches the identification accuracy of the original sample without data enhancement and transfer learning, whose accuracy are 92.1% and 92.5%.