Smile detection

We present a fully automated approach for smile detection. Faces are detected using a multi-view 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 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 is performed for smile detection. Experimental results show that our proposal outperforms state-of-the-art methods on both high and low quality images.

Additional material
Additional material (pdf)



Robust Smile Detection using Convolutional Neural Networks
(Simone Bianco, Luigi Celona, Raimondo Schettini) In Journal of Electronic Imaging, volume 25, number 6, pp. 063002, SPIE, 2016.

 author = {Bianco, Simone and Celona, Luigi and Schettini, Raimondo},
 year = {2016},
 pages = {063002},
 title = {Robust Smile Detection using Convolutional Neural Networks},
 volume = {25},
 number = {6},
 publisher = {SPIE},
 journal = {Journal of Electronic Imaging},
 pdf = {/download/bianco2016robust-smile.pdf},
 doi = {10.1117/1.JEI.25.6.063002}}