基于多特征融合的油画艺术风格分类  

Classification of Oil Painting Art Style Based on Multi-feature Fusion

作　　者：谢秦秦 何朗[1] 徐汝利 XIE Qinqin;HE Lang;XU Ruli(School of Science,Wuhan University of Technology,Wuhan 430070,China)

机构地区：[1]武汉理工大学理学院,武汉430070

出　　处：《计算机科学》2023年第3期223-230,共8页Computer Science

基　　金：国家自然科学基金(61672391)。

摘　　要：针对现有油画艺术风格分类算法忽略画面主体区域与整体效果对其艺术风格影响的问题,提出了一种基于多特征融合的油画分类算法(Multi-Feature Fusion Classifier,MFFC)。首先,基于油画艺术元素间常见的排列形式,设计重叠式图像分块法,提取油画空间特征,弥补现有算法中的构图风格缺失,同时区分主体区域与背景区域;其次,将空间特征与底层特征串联融合,增加画面元素的位置信息;最后,设计空间票选法,优先将主体区域的分类结果作为算法结果输出,进一步突出油画主体区域在分类中的作用,实现油画艺术风格的自动分类。在FS-Classifier模型创建的数据集上对所提算法进行测试,其准确率、精确率、召回率、F1-score和AUC分别为96.92%,63.69%,98.75%,98.57%和0.917,相比FS-Classifier分别提升了6.72%,5.85%,9.05%,7.1%和0.128;在公共数据集WIKIART上进行测试,并与其他6种算法进行比较,准确率至少提升了13.27%。实验结果表明,该算法有效提高了空间特征对油画艺术风格分类任务的表现性能,具有良好的实用价值。The existing oil painting art style classification algorithms ignore the influence of the main area and the overall effect on the art style.Aiming at this problem,this paper proposes a new oil painting classification algorithm based on multi-feature fusion classifier(MFFC).Firstly,based on the common arrangement form of oil painting art elements,this paper designs the overlapping image block method.This method extracts spatial features of oil paintings to make up for the lack of composition style in existing algorithms.And it also can be used to distinguish the subject area from the background area.Secondly,the spatial features and the underlying features are combined in series to increase the location information of the elements in the picture.Finally,the spatial voting method is designed to give priority to the classification result of the main area as the output result of the algorithm.This is to highlight the role of oil painting subject area in the classification and realize the automatic classification of oil painting art style.Tested on the data set created by the FS-classifier model,its accuracy,precision,recall,F1-score and AUC reaches 96.92%,63.69%,98.75%,98.57%and 0.917,respectively.Compared with FS-classifier,the result increases by 6.72%,5.85%,9.05%,7.1%and 0.128,respectively.When tested on WIKIART and compared with other six algorithms,the accuracy improves by 13.27%,at least.The results show that the proposed algorithm can effectively improve the performance of spatial features for oil painting art style classification task,and has good practical value.

关 键 词：油画艺术风格 图像分类 空间特征 特征融合 空间票选法 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]