ELM based smile detection using Distance Vector. (July 2018)

• Record Type: Journal Article
• Authors: Cui, Dongshun; Huang, Guang-Bin; Liu, Tianchi
• Is Part Of: Pattern recognition. Volume 79(2018:Jul.)
• Page Start: 356
• Page End: 369
• Publication Date: 2018-07
• Subjects: Smile detection -- Pair-wise Distance Vector -- Extreme Learning Machine; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2018.02.019
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We verified the effectiveness of mouth deformation as an indicator of a smile. We proposed a novel feature descriptor for smile detection. The proposed method outperforms other methods on accuracy and effectiveness. We improved GENKI-4K benchmark by relabeling and removing duplications. Abstract: The Smile is one of the most common facial expressions, and it serves as an indicator of the positive emotion. Many feature extraction methods have been proposed for detecting a smile in an unconstrained scene. However, most of the existing feature descriptors are too large and not effective to be applied to distinguish smile and non-smile in the real world. In this paper, we proposed an ELM-based smile detection system by using a novel feature extraction method. Motivated by the observation that the mouth shape can effectively reflect a person's smile state, a novel and snappy set of features from a few of facial landmarks around the mouth are extracted. We have tested our algorithms on the smile detection database, and the results indicate that our method is better than the state-of-the-art methods with higher accuracy and lower dimension of features.