论文标题
用卷积神经网络分析荷兰主画
Analysis of Dutch Master Paintings with Convolutional Neural Networks
论文作者
论文摘要
经过研究的艺术家的作品和其他艺术家的视觉可比性作品培训，卷积神经网络可以识别伪造并提供归因。他们还可以在绘画中分配分类概率，揭示混合作者身份并识别由不同手绘制的区域。
Trained on the works of an artist under study and visually comparable works of other artists, convolutional neural networks can identify forgeries and provide attributions. They can also assign classification probabilities within a painting, revealing mixed authorship and identifying regions painted by different hands.
