Affiliation:
1. University of Washington
2. Adobe Systems, Inc.
Abstract
In this paper, we train a computer to select still frames from video that work well as candid portraits. Because of the subjective nature of this task, we conduct a human subjects study to collect ratings of video frames across multiple videos. Then, we compute a number of features and train a model to predict the average rating of a video frame. We evaluate our model with cross-validation, and show that it is better able to select quality still frames than previous techniques, such as simply omitting frames that contain blinking or motion blur, or selecting only smiles. We also evaluate our technique qualitatively on videos that were not part of our validation set, and were taken outdoors and under different lighting conditions.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Reference22 articles.
1. The Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting Psychologists Press, 577 College Avenue, Palo Alto;Ekman P.;California,1978
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献