Novel Evaluation Metrics for Seam Carving based Image Retargeting
This work addresses the problem of evaluating image retargeting methods for researchers and practitioners, but it is incremental as it builds on existing seam carving techniques.
The paper tackles the lack of methodological evaluation for image retargeting by introducing two novel metrics as proxies for user ratings and using a salient object dataset as a benchmark, finding that humans generally agree with these metrics and some importance map methods are consistently more favorable.
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.