Sparse Representation Based Complete Kernel Marginal Fisher Analysis Framework for Computational Art Painting Categoriza
This paper presents a sparse representation based complete kernel marginal Fisher analysis (SCMFA) framework for categorizing fine art images. First, we introduce several Fisher vector based features for feature extraction so as to extract and encode impo
- PDF / 1,733,201 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 83 Downloads / 181 Views
Abstract. This paper presents a sparse representation based complete kernel marginal Fisher analysis (SCMFA) framework for categorizing fine art images. First, we introduce several Fisher vector based features for feature extraction so as to extract and encode important discriminatory information of the painting image. Second, we propose a complete marginal Fisher analysis method so as to extract two kinds of discriminant information, regular and irregular. In particular, the regular discriminant features are extracted from the range space of the intraclass compactness using the marginal Fisher discriminant criterion whereas the irregular discriminant features are extracted from the null space of the intraclass compactness using the marginal interclass separability criterion. The motivation for extracting two kinds of discriminant information is that the traditional MFA method uses a PCA projection in the initial step that may discard the null space of the intraclass compactness which may contain useful discriminatory information. Finally, we learn a discriminative sparse representation model with the objective to integrate the representation criterion with the discriminant criterion in order to enhance the discriminative ability of the proposed method. The effectiveness of the proposed SCMFA method is assessed on the challenging Painting-91 dataset. Experimental results show that our proposed method is able to (i) achieve the state-of-the-art performance for painting artist and style classification, (ii) outperform other popular image descriptors and deep learning methods, (iii) improve upon the traditional MFA method as well as (iv) discover the artist and style influence to understand their connections in different art movement periods.
1
Introduction
Fine art painting categorization and analysis is an emerging research area in computer vision, which is gaining increasing popularity in the recent years. Pioneer works in cognitive psychology [1,2] believe that the analysis of visual art is a complex cognitive task and requires involvement of multiple centers in the human brain in order to process different elements of visual art such as color, shapes, boundaries and brush strokes. c Springer International Publishing AG 2016 B. Leibe et al. (Eds.): ECCV 2016, Part VIII, LNCS 9912, pp. 612–627, 2016. DOI: 10.1007/978-3-319-46484-8 37
Sparse Representation Based Complete Kernel MFA Framework
613
From the computer vision point of view, unlike conventional image classification tasks, computational painting categorization exhibits two important issues for artist classification and style classification respectively. First, as for the artist classification, there are large variations in appearance, topics and styles within the paintings of the same artist. Second, as for the style classification, the inherent similarity gap between paintings within the same style is much larger compared to other image classification tasks such as object recognition and face recognition where the images of the same class have a lower varianc
Data Loading...