Sciweavers

Share
MIR
2010
ACM

ACQUINE: aesthetic quality inference engine - real-time automatic rating of photo aesthetics

8 years 11 months ago
ACQUINE: aesthetic quality inference engine - real-time automatic rating of photo aesthetics
We present ACQUINE - Aesthetic Quality Inference Engine, a publicly accessible system which allows users to upload their photographs and have them rated automatically for aesthetic quality. The system integrates a support vector machine based classifier which extracts visual features on the fly and performs real-time classification and prediction. As the first publicly available tool for automatically determining the aesthetic value of an image, this work is a significant first step in recognizing human emotional reaction to visual stimulus. In this paper, we discuss fundamentals behind this system, and some of the challenges faced while creating it. We report statistics generated from over 140,000 images uploaded by Web users. The system is demonstrated at http://acquine.alipr.com. Categories and Subject Descriptors H.4.m [Information Systems Applications]: Miscellaneous; I.5.4 [Pattern Recognition]: Applications General Terms Algorithm, Experimentation Keywords Aesthetics, Ima...
Ritendra Datta, James Ze Wang
Added 28 May 2010
Updated 28 May 2010
Type Conference
Year 2010
Where MIR
Authors Ritendra Datta, James Ze Wang
Comments (0)
books