基于多特征融合的油画艺术风格分类

doi:10.11896/jsjkx.211200110

摘要/Abstract

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。

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

Abstract: 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.

Key words: Art style of oil painting, Image classification, Spatial feature, Feature fusion, Spatial voting

中图分类号:

TP319

谢秦秦, 何朗, 徐汝利. 基于多特征融合的油画艺术风格分类[J]. 计算机科学, 2023, 50(3): 223-230. https://doi.org/10.11896/jsjkx.211200110

XIE Qinqin, HE Lang, XU Ruli. Classification of Oil Painting Art Style Based on Multi-feature Fusion[J]. Computer Science, 2023, 50(3): 223-230. https://doi.org/10.11896/jsjkx.211200110

参考文献

[1]BAI R Y,GUO X Y,JIA C H,et al.Overview of ResearchMethods of Painting Aesthetics[J].Journal of Image andGra-phics,2019,24(11):1860-1881.
[2]WANG X R,HUANG Z C.Painter Artistic Style ExtractionMethod Based on Color Features[J].Journal of Computer Applications,2020,40(6):1818-1823.
[3]FLOREA C,TOCA C,GIESEKE F.Artistic Movement Recognition by Boosted Fusion of Color Structure and Topographic Description[C]//Proceedings of 17th IEEE Winter Conference on Applications of Computer Vision.Santa Rosa:IEEE,2017:569-577.
[4]LAMBERTI F,SANA A,PARAVATI G.Computer assistedanalysis of painting brushstrokes:digital image processing for unsupervised extraction of visible features from van Gogh's works[J].EURASIP Journal on Image and Video Processing,2014,2014(1):1-17.
[5]LI J,YAO L,HENDRIKS E.Rhythmic brushstrokes distin-guish van Gogh from his contemporaries:findings via automated brushstroke extraction[J].IEEE Transactions on Pattern Ana-lysis and Machine Intelligence,2011,34(6):1159-1176.
[6]CHEN T,YANG J.A novel multi-feature fusion method in merging information of heterogenous-view data for oil painting image feature extraction and recognition[J/OL].Frontiers in Neurorobotics,2021,15:95.https://www.frontiersin.org/articles/10.3389/fnbot.2021.709043/full.
[7]LEVY E,DAVID O,NETANYAHU N S.Painter Classification Using Genetic Algorithms[C]//Congress on Evolutionary.Institute of Electrical and Electronics Engineers,New York:IEEE,2013:3027-3034.
[8]BAI R Y,GUO X Y,JIA C H.Research on Emotion of Abstract Painting Based on Multi-Feature Fusion[J].Application Research of Computer,2021,38(2):587-590.
[9]DONG X,LI G,JIA Y,et al.Multiscale feature extraction from the perspectiveof graph for hob fault diagnosis using spectral graph wavelet transform combined with improved random forest[J].Measurement,2021,176(2):109178.
[10]DU L,LI L,WANG B,et al.Micro-doppler Feature Extraction Based on Time-frequency Spectrogram for Ground Moving Targets Classification with Low-resolution Radar[J].IEEE Sensors Journal,2016,16(10):3756-3763.
[11]LU Y,GUO C,LIN Y L,et al.Computational Aesthetics of Fine Art Painting:The State of the Art and Outlook[J].Acta Automatica Sinica,2020,46(11):2239-2259.
[12]LU Z K.Research on Image retrieval based on color and spatial features[D].Quanzhou:Huaqiao University,2005.
[13]WIDJAJA I,LEOW W K,WU F C.Identifying Painters fromColor Profiles of Skin Patches in Painting Images[C]//Procee-dings of the 2003 International Conference on Image Processing.Piscataway:IEEE,2003:831-845.
[14]JIA C H,GUO X Y,BAI R Y.Review of Feature Extraction Methods and Research on Affective Analysis for Paintings[J].Journal of Image and Graphics,2018,23(7):937-952.
[15]JIANG X W,ZHANG M X,ZHU Z S.Recognition of Chinese Finger Sign Language Based on Gray Level Co-occurrence Matrix and Fine Gaussian Support Vector Machine[J].Computer Science,2019,46(S2):303-308.
[16]BISHOP C M.Pattern Recognition and Machine Learning[M].New York:Springer,2006:2-26.
[17]ZHANG H Y,ZHANG J,HUANG J.Multi-label Image Classification Model Based on Graph Attention Network[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2022,39(1):34-41.
[18]WU J,XU J,DING T.Fine-grained Image Classification Algorithm Based on Ensemble Methods of Transfer Learning[J].Journal of Chongqing Technology and Business University(Na-tural Science Edition),2020,32(3):452-458.
[19]ZHOU X M,HU Y G,LIU W J,et al.Research on Urban Function Recognition Based on Multi-level Data Fusion Method[J].Computer Science,2021,48(9):50-58.
[20]WANG Z Y,ZHANG Y Z,LIU Y,et al.MFC-Net:Multi-feature fusion cross neural network for salient object detection[J].Image and Vision Computing,2021,113:104243.
[21]MUSBAH H,ALY H H,LITTLE T A.Energy management of hybrid energy system sources based on machine learning classification algorithms[J/OL].Electric Power Systems Research,2021,199:107436.https://www.sciencedirect.com/science/article/pii/S037877962100417X.
[22]HE X H,QIU F B,CHENG X J,et al.High-resolution Image Building Target Detection Based on Edge Feature Fusion[J].Computer Science,2021,48(9):140-145.
[23]AGARWAL S,KARNICKA H C,PANT N,et al.Genre and Style Based Painting Classification[C]//Winter Conference on Applications of Computer Vision.New York:IEEE,2015:588-594.
[24]HUANG X,ZHONG S H,XIAO Z.Fine-art painting classification via two-channel deep residual network[J].International Journal of Machine Learning and Cybernetics,2020,11(1):137-152.
[25]LECOUTRE A,NEGREVERGNE B,YEGR F.Recognizing Art Style Automatically in Painting with Deep Learning[C]//Proceeding of the 9th Asian Conference on Machine Learning.Seoul,Korea:PMLR,2017:327-342.
[26]ELGAMMAL A,MAZZONE M,LIU B,et al.The Shape of Art History in the Eyes of the Machine[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Louisiana:AAAI Press,2018,32(1):2183-2191.
[27]CETINIC E,LIPIC T,GRGIC S.Fine-tuning ConvolutionalNeural Networks for Fine Art Classification[J].Expert Systems With Applications,2018,114(DEC.):107-118.
[28]SANDOVAL C,PIROGOVA E,LECH M.Two-stage DeepLearning Approach to the Classification of Fine-art Paintings[J/OL].IEEE Access,2019,7:41770-41781.https://ieeexplore.ieee.org/abstract/document/8675906.

相关文章 15

[1]	白雪飞, 马亚楠, 王文剑. 基于特征融合的边缘引导乳腺超声图像分割方法 Segmentation Method of Edge-guided Breast Ultrasound Images Based on Feature Fusion 计算机科学, 2023, 50(3): 199-207. https://doi.org/10.11896/jsjkx.211200294
[2]	刘泽京, 邬楠, 黄抚群, 宋友. 基于知识图谱与协同过滤混合策略的在线编程评测系统题目推荐模型 Hybrid Programming Task Recommendation Model Based on Knowledge Graph and Collaborative Filtering for Online Judge 计算机科学, 2023, 50(2): 106-114. https://doi.org/10.11896/jsjkx.211200105
[3]	邹芸竹, 杜圣东, 滕飞, 李天瑞. 一种基于多模态深度特征融合的视觉问答模型 Visual Question Answering Model Based on Multi-modal Deep Feature Fusion 计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303
[4]	华杰, 刘学亮, 赵烨. 基于特征融合的小样本目标检测 Few-shot Object Detection Based on Feature Fusion 计算机科学, 2023, 50(2): 209-213. https://doi.org/10.11896/jsjkx.220500153
[5]	赵倩, 周冬明, 杨浩, 王长城. 残差注意力与多特征融合的图像去模糊 Image Deblurring Based on Residual Attention and Multi-feature Fusion 计算机科学, 2023, 50(1): 147-155. https://doi.org/10.11896/jsjkx.211100161
[6]	武红鑫, 韩萌, 陈志强, 张喜龙, 李慕航. 监督和半监督学习下的多标签分类综述 Survey of Multi-label Classification Based on Supervised and Semi-supervised Learning 计算机科学, 2022, 49(8): 12-25. https://doi.org/10.11896/jsjkx.210700111
[7]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[8]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[9]	杜丽君, 唐玺璐, 周娇, 陈玉兰, 程建. 基于注意力机制和多任务学习的阿尔茨海默症分类 Alzheimer's Disease Classification Method Based on Attention Mechanism and Multi-task Learning 计算机科学, 2022, 49(6A): 60-65. https://doi.org/10.11896/jsjkx.201200072
[10]	郁舒昊, 周辉, 叶春杨, 王太正. SDFA:基于多特征融合的船舶轨迹聚类方法研究 SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion 计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253
[11]	杨玥, 冯涛, 梁虹, 杨扬. 融合交叉注意力机制的图像任意风格迁移 Image Arbitrary Style Transfer via Criss-cross Attention 计算机科学, 2022, 49(6A): 345-352. https://doi.org/10.11896/jsjkx.210700236
[12]	杨健楠, 张帆. 一种结合双注意力机制和层次网络结构的细碎农作物分类方法 Classification Method for Small Crops Combining Dual Attention Mechanisms and Hierarchical Network Structure 计算机科学, 2022, 49(6A): 353-357. https://doi.org/10.11896/jsjkx.210200169
[13]	陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强. 基于外接圆半径差损失的实时安全帽检测算法 Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss 计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252
[14]	孙洁琪, 李亚峰, 张文博, 刘鹏辉. 基于离散小波变换的双域特征融合深度卷积神经网络 Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation 计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199
[15]	蓝凌翔, 池明旻. 基于特征注意力融合网络的遥感变化检测研究 Remote Sensing Change Detection Based on Feature Fusion and Attention Network 计算机科学, 2022, 49(6): 193-198. https://doi.org/10.11896/jsjkx.210500058

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed