Detecting Rule of Simplicity from Photos
  Long Mai     Yuzhen Niu     Yu-Chi Lai     Feng Liu  
Long Mai, Hoang Le, Yuzhen Niu, Yu-chi Lai, and Feng Liu. Detecting Rule of Simplicity from Photos. In ACM Multimedia '12: Proceedings of the 20th International Conference on Multimedia, Nara, Japan,
Abstract

Simplicity refers to one of the most important photography composition rules. Simplicity states that simplifying the image background can draw viewers’ attention to the subject of interest in a photograph and help them better comprehend and appreciate it. Understanding whether a photo respects photography rules or not facilitates photo quality assessment. In this paper, we present a method to automatically detect whether a photo is composed according to the rule of simplicity. We design features according to the definition, implementation and effect of the rule. First, we make use of saliency analysis to infer the subject of interest in a photo and measure its compactness. Second, we segment an image into background and foreground and measure the homogeneity within the background as another feature. Third, when looking at an image created with the rule of simplicity, different viewers tend to agree on what the subject of
interest is in this photo. We accordingly measure the consistency among various saliency detection results as a feature. We experiment with these features in a range of machine learning methods. Our experiments show that our methods, together with these features, provide an encouraging result in detecting the rule of simplicity in a photo.

Bibtex

@inproceedings{Mai2012,

author = {Mai, Long and Le, Hoang and Niu, Yuzhen and Lai, Yu-Chi and Liu, Feng},

title = {Detecting rule of simplicity from photos},

booktitle = {Proceedings of the 20th ACM international conference on Multimedia},

series = {MM '12},

year = {2012},

numpages = {4}

}

Acknowledgement

NCS101-2221-E-011-153

PDF