咨询与建议

看过本文的还看了

相关文献

该作者的其他文献

文献详情 >The logical style painting cla... 收藏

The logical style painting classifier based on Horn clauses and explanations (<i>l</i>-SHE)

基于角子句和解释油漆分类器的逻辑风格(-SHE)

作     者:Costa, Vicent Dellunde, Pilar Falomir, Zoe 

作者机构:Univ Autonoma Barcelona Dept Philosophy Campus UAB Bellaterra 08193 Spain Barcelona Grad Sch Math Bellaterra 08193 Spain Artificial Intelligence Res Inst Bellaterra 08193 Spain Univ Autonoma Barcelona Bellaterra 08193 Spain Univ Bremen Fac Comp Sci & Math Bremen Spatial Cognit Ctr D-28359 Bremen Germany 

出 版 物:《LOGIC JOURNAL OF THE IGPL》 (IGPL逻辑杂志)

年 卷 期:2021年第29卷第1期

页      面:96-119页

核心收录:

学科分类:01[哲学] 0701[理学-数学] 

基  金:Generalitat de Catalunya European Social Fund YERUN Research Mobility Award (Young European Research UNiversities, first edition, 2017/2018) European Union Generalitat de Catalunya [2017SGR-172] University of Bremen YERUN Research Mobility Award (Young European Research UNiversities, second edition, 2018/2019) BSCC RASO TIN2015-71799-C2-1-P CIMBVAL TIN2017-89758-R 

主  题:qualitative colour art fuzzy logics Horn clause logic programming classifier explainable AI 

摘      要:This paper presents a logical Style painting classifier based on evaluated Horn clauses, qualitative colour descriptors and Explanations (l-SHE). Three versions of l-SHE are defined, using rational Pavelka logic (RPL), and expansions of Godel logic and product logic with rational constants: RPL, G(Q) and (sic) (Q), respectively. We introduce a fuzzy representation of the more representative colour traits for the Baroque, the Impressionism and the Post-Impressionism art styles. The l-SHE algorithm has been implemented in Swi-Prolog and tested on 90 paintings of the QArt-Dataset and on 247 paintings of the Paintings-91-PIB dataset. The percentages of accuracy obtained in the QArt-Dataset for each l-SHE version are 73.3% (RPL), 65.6% (G(Q)) and 68.9% ((sic) (Q)). Regarding the Paintings-91-PIB dataset, the percentages of accuracy obtained for each l-SHE version are 60.2% (RPL), 48.2% (G(Q)) and 57.0% ((sic) (Q)). Our logic definition for the Baroque style has obtained the highest accuracy in both datasets, for all the l-SHE versions (the lowest Baroque case gets 85.6% of accuracy). An important feature of the classifier is that it provides reasons regarding why a painting belongs to a certain style. The classifier also provides reasons about why outliers of one art style may belong to another art style, giving a second classification option depending on its membership degrees to these styles.

读者评论 与其他读者分享你的观点

用户名:未登录
我的评分