We propose an approach to automatically generate photo-on-photo compositions using only a consumer's own image collection, without imposing a strong theme constraint dictated by typical background art designs. Our goal is to ensure adequate foreground and background photo sizing, avoid occlusion of important background photo content, and respect simple aesthetic rules in photo arrangement. We propose a novel image content redundancy measure to extract the informative zone, which is a rectangular region of the background photo that should not be occluded by foreground content. Background photo layout and foreground layout regions are then calculated based on a placement algorithm that deals with possible aspect ratio mismatch of the canvas and background photo, as well as cases of insufficient foreground photo layout area.
[1]
Brian A. Wandell,et al.
A spatial extension of CIELAB for digital color‐image reproduction
,
1997
.
[2]
Christof Koch,et al.
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
,
2009
.
[3]
Nanning Zheng,et al.
Learning to Detect a Salient Object
,
2011,
IEEE Transactions on Pattern Analysis and Machine Intelligence.
[4]
Daniel Tretter,et al.
Blocked recursive image composition with exclusion zones
,
2010,
DocEng '10.
[5]
Jun Xiao,et al.
MagicPhotobook: designer inspired, user perfected photo albums
,
2009,
MM '09.
[6]
Jun Xiao,et al.
Mixed-initiative photo collage authoring
,
2008,
ACM Multimedia.