UNDERSTANDING PHOTOGRAPHIC COMPOSITION THROUGH DATA-DRIVEN APPROACHES

被引：0

作者：

Mao, Dansheng ^{[1
]}

Kakarala, Ramakrishna ^{[1
]}

Rajan, Deepu ^{[1
]}

Castleman, Shannon Lee ^{[2
]}

机构：

[1] Nanyang Technol Univ, Sch Comp Engn, Singapore, Singapore

[2] Nanyang Technol Univ, Sch Arts Design & Media, Singapore, Singapore

来源：

VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 2 | 2010年

关键词：

Computational Aesthetics; Computer vision; Machine learning; Visual perception; Saliency model;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Many elements contribute to a photograph's aesthetic value, include context, emotion, color, lightness, and composition. Of those elements, composition, which is how the arrangement of subjects, background, and features work together, is both highly challenging, and yet amenable, for understanding with computer vision techniques. Choosing famous monochromic photographs for which the composition is the dominant aesthetic contributor, we have developed data-driven approaches to understand composition. We obtain two novel results. The first shows relationships between the composition styles of master photographers based on their works, as obtained by analyzing extracted SIFT features. The second result, which relies on data obtained from eye-tracking equipment on both expert photographers and novices, shows that there are significant differences between them in what is salient in a photograph's composition.

引用

页码：425 / 430

页数：6