Modeling the Importance of Faces in Natural Images


In this work we study the varying importance of faces in images. Face importance is found to be affected by the size and number of faces present. We collected a dataset of 152 face images with faces in different size and number of faces. We conducted a crowdsourcing experiment where we asked people to label the important regions of the images. Analyzing the results from the experiment, we propose a simple face-importance model, which is a 2D Gaussian function, to quantitatively represent the influence of the size and number of faces on the perceived importance of faces. The face-importance model is then tested for the application of salient-object detection. For this application, we create a new salient-objects dataset, consisting of both face images and non-face images, and also through crowdsourcing we collect the ground truth. We demonstrate that our face-importance model helps us to better locate the important, thus salient, objects in the images and outperforms state-of-the-art salient-object detection algorithms.



[ Paper ]      [ Slides ]      [ More examples ]      [ Code ]      [ Dataset ]     


Bin Jin, Gokhan Yildirim, Cheryl Lau, Appu Shaji, Maria V. Ortiz Segovia, Sabine Süsstrunk
Modeling the Importance of Faces in Natural Images
InSPIE/IS&T Electronic Imaging, 2015.

    title={Modeling the importance of faces in natural images},
    author={Jin, Bin and Yildirim, G{\"o}khan and Lau, Cheryl and Shaji, Appu and Segovia, M Ortiz and S{\"u}sstrunk, Sabine},
    booktitle={SPIE/IS\&T Electronic Imaging},
    organization={International Society for Optics and Photonics}}


The authors thank the anonymous reviewers for their useful comments and suggestions.