Novel Evaluation Metrics for Seam Carving based Image Retargeting

TL;DR

This paper introduces two new evaluation metrics for seam carving based image retargeting, validated against user ratings and a salient object dataset, to improve objective assessment of retargeted images.

Contribution

It proposes novel evaluation metrics as user rating proxies and analyzes importance maps using a salient object dataset for better retargeting assessment.

Findings

Humans generally agree with the new evaluation metrics.

Some importance map methods outperform others.

Salient object dataset serves as an effective benchmark.

Abstract

Image retargeting effectively resizes images by preserving the recognizability of important image regions. Most of retargeting methods rely on good importance maps as a cue to retain or remove certain regions in the input image. In addition, the traditional evaluation exhaustively depends on user ratings. There is a legitimate need for a methodological approach for evaluating retargeted results. Therefore, in this paper, we conduct a study and analysis on the prominent method in image retargeting, Seam Carving. First, we introduce two novel evaluation metrics which can be considered as the proxy of user ratings. Second, we exploit salient object dataset as a benchmark for this task. We then investigate different types of importance maps for this particular problem. The experiments show that humans in general agree with the evaluation metrics on the retargeted results and some importance map methods are consistently more favorable than others.