Paper Info
Title
Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study
Abstract
Automatic photo cropping is an important tool for improving visual quality of digital photos without resorting to tedious manual selection. Traditionally, photo cropping is accomplished by determining the best proposal window through visual quality assessment or saliency detection. In essence, the performance of an image cropper highly depends on the ability to correctly rank a number of visually similar proposal windows. Despite the ranking nature of automatic photo cropping, little attention has been paid to learning-to-rank algorithms in tackling such a problem. In this work, we conduct an extensive study on traditional approaches as well as ranking-based croppers trained on various image features. In addition, a new dataset consisting of high quality cropping and pairwise ranking annotations is presented to evaluate the performance of various baselines. The experimental results on the new dataset provide useful insights into the design of better photo cropping algorithms.
Year
DOI
Venue
2017
10.1109/WACV.2017.32
2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
Keywords
DocType
Volume
automatic image cropping algorithms,digital photos visual quality,ranking-based croppers,image features,pairwise ranking annotations
Conference
abs/1701.01480
ISSN
ISBN
Citations 
2472-6737
978-1-5090-4823-6
8
PageRank 
References 
Authors
0.47
36
6
Name
Order
Citations
PageRank
Yi-Ling Chen1211.70
Tzu-Wei Huang2171.72
Kai-Han Chang380.47
Yu-Chen Tsai480.47
Hwann-Tzong Chen582652.13
Bing-Yu Chen61132101.82