Statistical Analysis of Facial Expression on 3D Face Shapes

2011 ◽  
pp. 224-247
Author(s):  
Jacey-Lynn Minoi ◽  
Duncan Gillies
Keyword(s):  
Facial Expression ◽  
Expression Analysis ◽  
Three Dimensional ◽  
Verbal Communication ◽  
Expression Recognition ◽  
Coding System ◽  
Facial Muscles ◽  
Facial Expression Analysis ◽  
Craniofacial Features ◽  
Expression Of Emotions

The aim of this chapter is to identify those face areas containing high facial expression information, which may be useful for facial expression analysis, face and facial expression recognition and synthesis. In the study of facial expression analysis, landmarks are usually placed on well-defined craniofacial features. In this experiment, the authors have selected a set of landmarks based on craniofacial anthropometry and associate each of the landmarks with facial muscles and the Facial Action Coding System (FACS) framework, which means to locate landmarks on less palpable areas that contain high facial expression mobility. The selected landmarks are statistically analysed in terms of facial muscles motion based on FACS. Given that human faces provide information to channel verbal and non-verbal communication: speech, facial expression of emotions, gestures, and other human communicative actions; hence, these cues may be significant in the identification of expressions such as pain, agony, anger, happiness, et cetera. Here, the authors describe the potential of computer-based models of three-dimensional (3D) facial expression analysis and the non-verbal communication recognition to assist in biometric recognition and clinical diagnosis.

Facial Expression Recognition

2011 ◽  
pp. 255-317 ◽  
Author(s):  
Daijin Kim ◽  
Jaewon Sung
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Facial Expression Recognition ◽  
Muscle Group ◽  
Expression Recognition ◽  
Coding System ◽  
Facial Action Coding System ◽  
Multiple Cultures ◽  
Expression Of Emotions ◽  
Objective Description

The facial expression has long been an interest for psychology, since Darwin published The expression of Emotions in Man and Animals (Darwin, C., 1899). Psychologists have studied to reveal the role and mechanism of the facial expression. One of the great discoveries of Darwin is that there exist prototypical facial expressions across multiple cultures on the earth, which provided the theoretical backgrounds for the vision researchers who tried to classify categories of the prototypical facial expressions from images. The representative 6 facial expressions are afraid, happy, sad, surprised, angry, and disgust (Mase, 1991; Yacoob and Davis, 1994). On the other hand, real facial expressions that we frequently meet in daily life consist of lots of distinct signals, which are subtly different. Further research on facial expressions required an object method to describe and measure the distinct activity of facial muscles. The facial action coding system (FACS), proposed by Hager and Ekman (1978), defines 46 distinct action units (AUs), each of which explains the activity of each distinct muscle or muscle group. The development of the objective description method also affected the vision researchers, who tried to detect the emergence of each AU (Tian et. al., 2001).

scholarly journals THE TIMING OF FACIAL MOTION IN POSED AND SPONTANEOUS SMILES

2004 ◽  
Vol 02 (02) ◽  
pp. 121-132 ◽  
Author(s):  
J. F. COHN ◽  
K. L. SCHMIDT
Keyword(s):  
Facial Expression ◽  
Expression Analysis ◽  
Recognition Rate ◽  
Expression Recognition ◽  
Dynamic Features ◽  
Linear Discriminant ◽  
Facial Motion ◽  
Relative Contribution ◽  
Facial Expression Analysis ◽  
Almost All

Almost all work in automatic facial expression analysis has focused on recognition of prototypic expressions rather than dynamic changes in appearance over time. To investigate the relative contribution of dynamic features to expression recognition, we used automatic feature tracking to measure the relation between amplitude and duration of smile onsets in spontaneous and deliberate smiles of 81 young adults of Euro- and African-American background. Spontaneous smiles were of smaller amplitude and had a larger and more consistent relation between amplitude and duration than deliberate smiles. A linear discriminant classifier using timing and amplitude measures of smile onsets achieved a 93% recognition rate. Using timing measures alone, recognition rate declined only marginally to 89%. These findings suggest that by extracting and representing dynamic as well as morphological features, automatic facial expression analysis can begin to discriminate among the message values of morphologically similar expressions.

scholarly journals Facial Expression Analysis using Convolutional Neural Networks

2020 ◽  
Vol 9 (4) ◽  
pp. 1142-1146
Keyword(s):  
Neural Networks ◽  
Facial Expression ◽  
Real Time ◽  
Facial Expressions ◽  
Convolutional Neural Networks ◽  
Expression Analysis ◽  
Facial Expression Recognition ◽  
Expression Recognition ◽  
Real Time System ◽  
Facial Expression Analysis

Human feelings are mental conditions of sentiments that emerge immediately as opposed to cognitive exertion. Some of the basic feelings are happy, angry, neutral, sad and surprise. These internal feelings of a person are reflected on the face as Facial Expressions. This paper presents a novel methodology for Facial Expression Analysis which will aid to develop a facial expression recognition system. This system can be used in real time to classify five basic emotions. The recognition of facial expressions is important because of its applications in many domains such as artificial intelligence, security and robotics. Many different approaches can be used to overcome the problems of Facial Expression Recognition (FER) but the best suited technique for automated FER is Convolutional Neural Networks(CNN). Thus, a novel CNN architecture is proposed and a combination of multiple datasets such as FER2013, FER+, JAFFE and CK+ is used for training and testing. This helps to improve the accuracy and develop a robust real time system. The proposed methodology confers quite good results and the obtained accuracy may give encouragement and offer support to researchers to build better models for Automated Facial Expression Recognition systems.

Facial Action Recognition in 2D and 3D

2014 ◽  
pp. 167-186 ◽  
Author(s):  
Michel Valstar ◽  
Stefanos Zafeiriou ◽  
Maja Pantic
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Expression Analysis ◽  
Coding System ◽  
Recording Equipment ◽  
Facial Action ◽  
Facial Expression Analysis ◽  
Challenges And Opportunities ◽  
Almost All ◽  
2D And 3D

Automatic Facial Expression Analysis systems have come a long way since the earliest approaches in the early 1970s. We are now at a point where the first systems are commercially applied, most notably smile detectors included in digital cameras. As one of the most comprehensive and objective ways to describe facial expressions, the Facial Action Coding System (FACS) has received significant and sustained attention within the field. Over the past 30 years, psychologists and neuroscientists have conducted extensive research on various aspects of human behaviour using facial expression analysis coded in terms of FACS. Automating FACS coding would make this research faster and more widely applicable, opening up new avenues to understanding how we communicate through facial expressions. Mainly due to the cost effectiveness of existing recording equipment, until recently almost all work conducted in this area involves 2D imagery, despite their inherent problems relating to pose and illumination variations. In order to deal with these problems, 3D recordings are increasingly used in expression analysis research. In this chapter, the authors give an overview of 2D and 3D FACS recognition, and summarise current challenges and opportunities.

scholarly journals GAMBARAN MUSCULI FACIALIS PADA EKSPRESI WAJAH DAN EMOSI DENGAN MENGGUNAKAN FACIAL ACTION CODING SYSTEM PADA CALON PRESIDEN JOKOWI

2015 ◽  
Vol 3 (1) ◽  
Author(s):  
Friska G. Batoteng ◽  
Taufiq F. Pasiak ◽  
Shane H. R. Ticoalu
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Expression Recognition ◽  
Coding System ◽  
Facial Action Coding System ◽  
Orbicularis Oculi ◽  
Facial Action ◽  
Facial Muscles ◽  
The Face ◽  
Facial Action Coding

Abstract: Facial expression recognition is one way to recognize emotions which has not received much attention. Muscles that form facial expressions known as musculli facial, muscles that move the face and form human facial expressions: happy, sad, angry, fearful, disgusted and surprised which are the six basic expressions of human emotion. Human facial expressions can be measured using FACS (Facial Action Coding System). This study aims to determine the facial muscles which most frequently used and most rarely used, and determine the emotion expression of Jokowi, a presidential candidate, through assessment of the facial muscles using FACS. This study is a retrospective descriptive study. The research samples are the whole photo of Jokowi’s facial expression at first presidential debate in 2014, about 30 photos. Samples were taken from a video debate and confirmed to be a photo using Jokowi’s facial expressions which then further analyzed using FACS. The research showed that the most used action units and facial muscle is AU 1 whose work on frontal muscle pars medialis (14.75%). The least appear muscles on Jokowi’s facial expressions were musculus orbicularis oculi, pars palpebralis and AU 24 musculus obicularis oris (0.82%). The dominant facial expressions was seen in Jokowi was sad facial expression (36.67%).Keywords: musculi facialis, facial expression, expression of emotion, FACSAbstrak: Pengenalan ekspresi wajah adalah salah satu cara untuk mengenali emosi yang belum banyak diperhatikan. Otot-otot yang membentuk ekspresi wajah yaitu musculli facialis yang merupakan otot-otot penggerak wajah dan membentuk ekspresi – ekspresi wajah manusia yaitu bahagia, sedih, marah, takut, jijik dan terkejut yang merupakan 6 dasar ekspresi emosi manusia. Ekspresi wajah manusia dapat diukur dengan menggunakan parameter FACS (Facial Action Coding System). Penelitian ini bertujuan untuk mengetahui musculi facialis yang paling sering digunakan dan yang paling jarang digunakan, serta untuk menentukan ekspresi emosi calon presiden Jokowi. Desain penelitian ini yaitu penelitian deskriptif dengan retrospektif. Sampel penelitian ialah seluruh foto ekspresi wajah Jokowi saat debat calon presiden pertama tahun 2014 sebanyak 30 foto. Sampel diambil dari video debat dan dikonfirmasi menjadi foto kemudian dianalisis lebih lanjut menggunakan FACS. Penelitian ini didapatkan hasil bahwa Musculi yang paling banyak digerakkan, yaitu Musculi frontalis pars medialis (14,75%). Musculi yang paling sedikit muncul pada ekspresi wajah Jokowi yaitu musculus orbicularis oculi, pars palpebralis dan musculus obicularis oris (0,82%). Ekspresi wajah yang dominan dinampakkan oleh Jokowi merupakan ekspresi wajah sedih (36,67%).Kata kunci: musculi facialis, ekspresi wajah, ekspresi emosi, FACS

scholarly journals 3D Approaches and Challenges in Facial Expression Recognition Algorithms—A Literature Review

2019 ◽  
Vol 9 (18) ◽  
pp. 3904 ◽  
Author(s):  
Francesca Nonis ◽  
Nicole Dagnes ◽  
Federica Marcolin ◽  
Enrico Vezzetti
Keyword(s):  
Facial Expression ◽  
Technological Development ◽  
Three Dimensional ◽  
3D Analysis ◽  
Expression Recognition ◽  
Interaction Domain ◽  
Still Images ◽  
Facial Expression Analysis ◽  
Viable Solution ◽  
Active Research

In recent years, facial expression analysis and recognition (FER) have emerged as an active research topic with applications in several different areas, including the human-computer interaction domain. Solutions based on 2D models are not entirely satisfactory for real-world applications, as they present some problems of pose variations and illumination related to the nature of the data. Thanks to technological development, 3D facial data, both still images and video sequences, have become increasingly used to improve the accuracy of FER systems. Despite the advance in 3D algorithms, these solutions still have some drawbacks that make pure three-dimensional techniques convenient only for a set of specific applications; a viable solution to overcome such limitations is adopting a multimodal 2D+3D analysis. In this paper, we analyze the limits and strengths of traditional and deep-learning FER techniques, intending to provide the research community an overview of the results obtained looking to the next future. Furthermore, we describe in detail the most used databases to address the problem of facial expressions and emotions, highlighting the results obtained by the various authors. The different techniques used are compared, and some conclusions are drawn concerning the best recognition rates achieved.

scholarly journals Facial Expression Analysis Based on Fusion Multi-Layer Convolutional Layer Feature Neural Network

2020 ◽  
Author(s):  
Hao Meng ◽  
Fei Yuan ◽  
Tianhao Yan
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Expression Analysis ◽  
Recognition Rate ◽  
Expression Recognition ◽  
Feature Vectors ◽  
Facial Expression Analysis ◽  
Deep Feature ◽  
Feature Information ◽  
The Stability

Concerning the problem that the current facial expression analysis based on convolutional neural network (CNN) only uses the features of the last convolutional layer but the recognition rate is not high, this paper proposes the use of sub-deep convolutional layer features and builds a CNN model which fuses the features of multi-layer convolutional layers. The model uses a CNN for feature extraction and saves the deepest feature vectors and sub-deep feature vectors of the expression images. The sub-deep feature vector is used as the input of the multilayer CNN established in this paper. The processed fourth convolution layer feature is fused with the deepest feature previously saved to perform facial expression analysis. Experiments are performed on FERPLUS dataset, Cohn-Kanade dataset (CK+) and JAFFE dataset. The experimental results show that the improved network structure proposed in this paper can capture richer feature information during facial expression analysis, which greatly improves the accuracy of expression recognition and the stability of the network. Compared with the original CNN-based facial expression analysis using only the last layer of convolution layer features, using multi-layer fusion features on three kinds of datasets can improve the expression recognition rate by 33.3%, 2.3% and 22%, respectively.

Sign in / Sign up

Export Citation Format

Share Document