A new pipeline for the recognition of universal expressions of multiple faces in a video sequence
- PDF / 2,192,356 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 46 Downloads / 170 Views
ORIGINAL RESEARCH PAPER
A new pipeline for the recognition of universal expressions of multiple faces in a video sequence Latifa Greche1 · Mohamed Akil2 · Rostom Kachouri2 · Najia Es‑sbai1 Received: 9 December 2018 / Accepted: 26 June 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Facial expression recognition (FER) is a crucial issue in human–machine interaction. It allows machines to act according to facial expression changes. However, acting in real time requires recognizing the expressions at video speed. Usually, the video speed differs from one device to another. However, one of the standard settings for shooting videos is 24 fps. This speed is considered as the low end of what our brain can perceive as fluid video. From this perspective, to achieve a real-time FER, the image analysis must be completed, strictly, in less than 0.042 s no matter how the background complexity is or how many faces exists in the scene. In this paper, a new pipeline has been proposed to recognize the fundamental facial expressions for more than one person in real-world sequence videos. First, the pipeline takes as input a video and performs a face detection and tracking. Regions of Interest (ROI) are extracted from the detected face to extract the shape information when applying the histogram of oriented gradient (HOG) descriptor. The number of features yield by HOG descriptor is reduced by means of a linear discriminant analysis (LDA). Then, a deep data analysis was carried out, exploiting the pipeline, for the objective of setting up the LDA classifier. The analysis aimed at proving the suitability of the decision rule selected to separate the facial expression clusters in the LDA training phase. To conduct our analysis, we used ChonKanade (CK+) database and F-measure as an evaluation metric to calculate the average recognition rates. An automatic evaluation over time is proposed, where labelled videos is utilized to investigate the suitability of the pipeline in real-world condition. The pipeline results showed that the use of HOG descriptor and the LDA gives a high recognition rate of 94.66%. It should be noted that the proposed pipeline achieves an average processing time of 0.018 s, without requiring any device that speeds up the processing. Keywords Facial expression recognition · Histogram of oriented gradient · Linear discriminant analysis
1 Introduction The early studies and analysis of facial expressions were studied only in the psychological field where Charles Darwin [1] demonstrated for the first time that despite the differences between individuals and cultures, six facial expressions are innate and common among human beings, which are joy, fear, sadness, surprise, anger, and disgust. With the emergence of new technologies and robots, the psychologist provided * Latifa Greche [email protected] Mohamed Akil [email protected] 1
Laboratoire énergies renouvelables et systèmes intelligents, Faculté des Sciences et Techniques, USMBA, Fès, Maroc
Laboratoire d’Informatique
Data Loading...
