Facial Expression Recognition from World Wild Web

TL;DR

This study explores recognizing facial expressions from uncontrolled web images using deep neural networks, achieving over 82% accuracy despite noisy data collected from internet sources.

Contribution

The paper introduces a new approach for collecting, annotating, and analyzing wild facial expressions from the web using multiple languages and search engines.

Findings

Deep neural networks achieved 82.12% accuracy in recognizing wild facial expressions.

Web-collected images with noise can be effectively used for training facial expression recognition models.

Multi-language web queries enhance the diversity of facial expression datasets.

Abstract

Recognizing facial expression in a wild setting has remained a challenging task in computer vision. The World Wide Web is a good source of facial images which most of them are captured in uncontrolled conditions. In fact, the Internet is a Word Wild Web of facial images with expressions. This paper presents the results of a new study on collecting, annotating, and analyzing wild facial expressions from the web. Three search engines were queried using 1250 emotion related keywords in six different languages and the retrieved images were mapped by two annotators to six basic expressions and neutral. Deep neural networks and noise modeling were used in three different training scenarios to find how accurately facial expressions can be recognized when trained on noisy images collected from the web using query terms (e.g. happy face, laughing man, etc)? The results of our experiments show that deep neural networks can recognize wild facial expressions with an accuracy of 82.12%.