SmileNet: Registration-Free Smiling Face Detection In The Wild

Abstract

We present a novel smiling face detection framework called SmileNet for detecting faces and recognising smiles in the wild. SmileNet uses a Fully Convolutional Neural Network (FCNN) to detect multiple smiling faces in a given image of varying resolution. Our contributions are threefold: 1) SmileNet is the first smiling face detection network that does not require pre-processing such as face detection and registration in advance to generate a normalised (cropped and aligned) input image; 2) the proposed SmileNet is a simple and single FCNN architecture simultaneously performing face detection and smile recognition, which are conventionally treated as separate consecutive pipelines; and 3) SmileNet ensures real-time processing speed (21.15 FPS) even when detecting multiple smiling faces in a given image (300X300). Experimental results show that SmileNet can deliver state-of-the-art performance (95.76%), even under occlusions, and variances of pose, scale, and illumination.

Publication

Youngkyoon Jang, Hatice Gunes, Ioannis Patras

SmileNet: Registration-Free Smiling Face Detection In The Wild

IEEE International Conference on Computer Vision Workshop (ICCVW), Venice, Italy, Oct. 22-29, 2017. (Oral)

Workshop: 7th IEEE International Workshop on Analysis and Modeling of Faces and Gestures (AMFG)

Download: [PDF], [Demo1 / Demo2 / Demo3 on Youtube Video] [Publicising Page]

Relevant Publication (Extended version, 26% overlapped with ICCVW version)

Dataset

* Download: Bounding box labels for GENKI-4K dataset

* Bounding box label format: ['x, y coordinates' of the upper left corner of a bounding box and its 'width, height']

* We annotated the bounding box label for the GENKI-4K dataset. If you use the label, please quote our paper.

Online Demo Video

Acknowledgement

This work is supported by the Technology Strategy Board / Innovate UK project Sensing Feeling (project no. 102547).

Link

Author URL: [Youngkyoon Jang], [Hatice Gunes], [Ioannis Patras]

Affiliation URL: [Multimedia and Vision Group] (Queen Mary University of London), [Computer Laboratory] (University of Cambridge)