A Geometry-Sensitive Approach for Photographic Style Classification
Item Type:Conference Paper
Citation:Ghosal, K., Prasad, M. & Smolic, A. 'A Geometry-Sensitive Approach for Photographic Style Classification', Irish Machine Vision and Image Processing Conference, Belfast, 2018
Photographs are characterized by different compositional attributes like the Rule of Thirds, depth of field, vanishing-lines etc. The presence or absence of one or more of these attributes contributes to the overall artistic value of an image. In this work, we analyze the ability of deep learning based methods to learn such photographic style attributes. We observe that although a standard CNN learns the texture and appearance based features reasonably well, its understanding of global and geometric features is limited by two factors. First, the data-augmentation strategies (cropping, warping, etc.) distort the composition of a photograph and affect the performance. Secondly, the CNN features, in principle, are translationinvariant and appearance-dependent. But some geometric properties important for aesthetics, e.g. the Rule of Thirds (RoT), are position-dependent and appearance-invariant. Therefore, we propose a novel input representation which is geometry-sensitive, position-cognizant and appearance-invariant. We further introduce a two-column CNN architecture that performs better than the state-of-the-art (SoA) in photographic style classification. From our results, we observe that the proposed network learns both the geometric and appearance-based attributes better than the SoA.
Science Foundation Ireland (SFI)
Other Titles:Irish Machine Vision and Image Processing Conference 2018 (IMVIP), 2018.
Type of material:Conference Paper
Availability:Full text available