Categorizing paintings in art styles based on qualitative color descriptors, quantitative global features and machine learning (QArt-Learn)
作者：
Highlights：
• QArt-Learn categorizes Baroque, Impressionism and Post-Impressionism painting styles.
• It uses Qualitative Colors (QC) that describe style color palettes linguistically.
• K-NN and SVM classifiers learned QCs and global average features of paintings.
• A 252-painting-set was extracted from Painting-91 corresponding to these styles.
• Accuracy of categorization higher than 65% was obtained in this dataset.
摘要
•QArt-Learn categorizes Baroque, Impressionism and Post-Impressionism painting styles.•It uses Qualitative Colors (QC) that describe style color palettes linguistically.•K-NN and SVM classifiers learned QCs and global average features of paintings.•A 252-painting-set was extracted from Painting-91 corresponding to these styles.•Accuracy of categorization higher than 65% was obtained in this dataset.
论文关键词：Qualitative modelling,Color naming,Color similarity,Support vector machines,Art,Machine learning
论文评审过程：Received 31 July 2017, Revised 17 October 2017, Accepted 30 November 2017, Available online 2 December 2017, Version of Record 19 December 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.056
