1. Landmark triangulation-induced Altitude Signature for change detection of human emotion from face image sequence.
- Author
-
Nasir, Md, Dutta, Paramartha, and Nandi, Avishek
- Abstract
Video-based facial expression recognition is a potential alternative for detecting the transitional processes of human emotion. In this paper, we present the landmark triangulation-induced altitude signatures to depict gradual changes in human emotion from face video frames. In our proposed approach, we consider the geometry-based triangulation technique which results from the triangles formed by important landmark points on face images. In this work, we measure three altitudes from all triangles and generate three different variations of altitude signature viz. AS1, AS2 and AS3 for the classification of six basic emotions viz. anger (AN), disgust (DI), fear (FE), happiness (HA), sadness (SA) and surprise (SU) in several ways. The performance capability of our proposed recognition system is tested on three benchmark face video datasets: Extended Cohn–Kanade (CK+), M&M Initiative (MMI), and Multimedia Understanding Group (MUG) through the application of Multilayer Perceptron (MLP) classifier and also validated by tenfold cross-validation method. Experimental results, 98.77%, 93.06%, and 98.75% on CK+, MMI, and MUG, respectively, are found very impressive. System efficacy is vindicated by showing the superiority of the proposed technique over the other existing techniques. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF