SOM based artistic styles visualization

Painting collections from the old masters are valuable cultural heritage of human history. Their artistic styles can be generally determined by their art periods. From analyzing and visualizing the relationships of different artistic styles, information can be found to facilitate art history studies. In this paper, we propose a Self-organizing Map (SOM) based framework specifically for analyzing and visualizing the relationships among painting collections from artistic perspectives. In our framework, we first define a set of image features based on artistic concepts used in art criticism; then a SOM-based hierarchical model is used to analyze features extracted from individual artists' painting collections. For our experiments, we obtain painting collections of six painting masters representing three art movements: post-impressionism, cubism and renaissance. An interactive web interface is also built to present our artistic influence analysis results. Through our experimental results, styles of different painting collections and their influential relationships can be analyzed and visualized from artistic perspectives.

[1]  Lior Shamir,et al.  Impressionism, expressionism, surrealism: Automated recognition of painters and schools of art , 2010, TAP.

[2]  M C PAYNE,et al.  Apparent weight as a function of color. , 1958, American Journal of Psychology.

[3]  Bryan Pardo,et al.  Classifying paintings by artistic genre: An analysis of features & classifiers , 2009, 2009 IEEE International Workshop on Multimedia Signal Processing.

[4]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[5]  Marion Monroe,et al.  The Apparent Weight of Color and Correlated Phenomena , 1925 .

[6]  Ulrich Ansorge,et al.  Salience in Paintings: Bottom-Up Influences on Eye Fixations , 2011, Cognitive Computation.

[7]  Erkki Oja,et al.  PicSOM - A Framework for Content-Based Image Database Retrieval using Self-Organizing Maps , 1999 .

[8]  Oguz Icoglu,et al.  Content-based access to art paintings , 2005, IEEE International Conference on Image Processing 2005.

[9]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[10]  Giovanni Soda,et al.  Transformation invariant SOM clustering in Document Image Analysis , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[11]  Payne Mc.  Apparent weight as a function of color. , 1958 .

[12]  Sung-Hyuk Cha,et al.  The classification of style in fine-art painting , 2005 .

[13]  Jeremiah D. Deng.  Content-based comparison of image collections via distance measuring of self-organised maps , 2004, 10th International Multimedia Modelling Conference, 2004. Proceedings..

[14]  Mateja Culjak,et al.  Classification of art paintings by genre , 2011, 2011 Proceedings of the 34th International Convention MIPRO.

[15]  Masahiro Takatsuka,et al.  A Framework Towards Quantified Artistic Influences Analysis , 2012, 2012 International Conference on Digital Image Computing Techniques and Applications (DICTA).

[16]  Ramesh C. Jain,et al.  Annotation of paintings with high-level semantic concepts using transductive inference and ontology-based concept disambiguation , 2007, ACM Multimedia.

[17]  Ramesh C. Jain,et al.  Representation and retrieval of paintings based on art history concepts , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[18]  Alberto Del Bimbo,et al.  Retrieval of paintings using effects induced by color features , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.

[19]  Lois Fichner-Rathus.  Foundations of Art and Design , 2007 .

[20]  Erkki Oja,et al.  PicSOM: self-organizing maps for content-based image retrieval , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[21]  James Ze Wang,et al.  Studying digital imagery of ancient paintings by mixtures of stochastic models , 2004, IEEE Transactions on Image Processing.