Abstract
Automatic understanding of photo composition is a valuable technology in multiple areas including digital photography, multimedia advertising, entertainment, and image retrieval. In this paper, we propose a method to model geometrically the compositional effects of linear perspective. Comparing with existing methods which have focused on basic rules of design such as simplicity, visual balance, golden ratio, and the rule of thirds, our new quantitative model is more comprehensive whenever perspective is relevant. We first develop a new hierarchical segmentation algorithm that in-tegrates classic photometric cues with a new geometric cue inspired by perspective geometry. We then show how these cues can be used directly to detect the dominant vanish-ing point in an image without extracting any line segments, a technique with implications for multimedia applications beyond this work. Finally, we demonstrate an interesting application of the proposed method for providing on-site composition feedback through an image retrieval system.
Original language | English (US) |
---|---|
Title of host publication | MM 2015 - Proceedings of the 2015 ACM Multimedia Conference |
Publisher | Association for Computing Machinery, Inc |
Pages | 301-310 |
Number of pages | 10 |
ISBN (Electronic) | 9781450334594 |
DOIs | |
State | Published - Oct 13 2015 |
Event | 23rd ACM International Conference on Multimedia, MM 2015 - Brisbane, Australia Duration: Oct 26 2015 → Oct 30 2015 |
Publication series
Name | MM 2015 - Proceedings of the 2015 ACM Multimedia Conference |
---|
Other
Other | 23rd ACM International Conference on Multimedia, MM 2015 |
---|---|
Country | Australia |
City | Brisbane |
Period | 10/26/15 → 10/30/15 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Media Technology
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition
- Software
Cite this
}
Modeling perspective effects in photographic composition. / Zhou, Zihan; He, Siqiong; Li, Jia; Wang, James Z.
MM 2015 - Proceedings of the 2015 ACM Multimedia Conference. Association for Computing Machinery, Inc, 2015. p. 301-310 (MM 2015 - Proceedings of the 2015 ACM Multimedia Conference).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Modeling perspective effects in photographic composition
AU - Zhou, Zihan
AU - He, Siqiong
AU - Li, Jia
AU - Wang, James Z.
PY - 2015/10/13
Y1 - 2015/10/13
N2 - Automatic understanding of photo composition is a valuable technology in multiple areas including digital photography, multimedia advertising, entertainment, and image retrieval. In this paper, we propose a method to model geometrically the compositional effects of linear perspective. Comparing with existing methods which have focused on basic rules of design such as simplicity, visual balance, golden ratio, and the rule of thirds, our new quantitative model is more comprehensive whenever perspective is relevant. We first develop a new hierarchical segmentation algorithm that in-tegrates classic photometric cues with a new geometric cue inspired by perspective geometry. We then show how these cues can be used directly to detect the dominant vanish-ing point in an image without extracting any line segments, a technique with implications for multimedia applications beyond this work. Finally, we demonstrate an interesting application of the proposed method for providing on-site composition feedback through an image retrieval system.
AB - Automatic understanding of photo composition is a valuable technology in multiple areas including digital photography, multimedia advertising, entertainment, and image retrieval. In this paper, we propose a method to model geometrically the compositional effects of linear perspective. Comparing with existing methods which have focused on basic rules of design such as simplicity, visual balance, golden ratio, and the rule of thirds, our new quantitative model is more comprehensive whenever perspective is relevant. We first develop a new hierarchical segmentation algorithm that in-tegrates classic photometric cues with a new geometric cue inspired by perspective geometry. We then show how these cues can be used directly to detect the dominant vanish-ing point in an image without extracting any line segments, a technique with implications for multimedia applications beyond this work. Finally, we demonstrate an interesting application of the proposed method for providing on-site composition feedback through an image retrieval system.
UR - http://www.scopus.com/inward/record.url?scp=84962808568&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962808568&partnerID=8YFLogxK
U2 - 10.1145/2733373.2806248
DO - 10.1145/2733373.2806248
M3 - Conference contribution
AN - SCOPUS:84962808568
T3 - MM 2015 - Proceedings of the 2015 ACM Multimedia Conference
SP - 301
EP - 310
BT - MM 2015 - Proceedings of the 2015 ACM Multimedia Conference
PB - Association for Computing Machinery, Inc
ER -