14 November 2016 Robust smile detection using convolutional neural networks
Author Affiliations +
We present a fully automated approach for smile detection. Faces are detected using a multiview face detector and aligned and scaled using automatically detected eye locations. Then, we use a convolutional neural network (CNN) to determine whether it is a smiling face or not. To this end, we investigate different shallow CNN architectures that can be trained even when the amount of learning data is limited. We evaluate our complete processing pipeline on the largest publicly available image database for smile detection in an uncontrolled scenario. We investigate the robustness of the method to different kinds of geometric transformations (rotation, translation, and scaling) due to imprecise face localization, and to several kinds of distortions (compression, noise, and blur). To the best of our knowledge, this is the first time that this type of investigation has been performed for smile detection. Experimental results show that our proposal outperforms state-of-the-art methods on both high- and low-quality images.
© 2016 SPIE and IS&T
Simone Bianco, Simone Bianco, Luigi Celona, Luigi Celona, Raimondo Schettini, Raimondo Schettini, } "Robust smile detection using convolutional neural networks," Journal of Electronic Imaging 25(6), 063002 (14 November 2016). https://doi.org/10.1117/1.JEI.25.6.063002 . Submission:


Research on subjective stereoscopic image quality assessment
Proceedings of SPIE (January 18 2009)
Fair benchmark for image watermarking systems
Proceedings of SPIE (April 08 1999)
Content-based image classification
Proceedings of SPIE (December 19 1999)

Back to Top