• Corpus ID: 7226645

3D facial expression intensity measurement analysis

  title={3D facial expression intensity measurement analysis},
  author={Cheong Chiek Ying Alicia and Ujir Hamimah and I. Hipiny},
This study used 3D distance vector measurements as the facial feature to classify six basic expressions and the distance vectors are chosen based on Facial Action Coding System (FACS) component, facial action units (AUs). The statistical values are calculated and analyze to determine the AUs involved in facial expression and distance vectors to be taken into account to measure the intensity of each facial expression in a quantitative manner. As a result, 14 facial points are classified as… 

Figures and Tables from this paper

The Analysis of Facial Feature Deformation using Optical Flow Algorithm
The study of facial feature deformation for each facial expression by using an optical flow algorithm and segmented into three different regions of interest suggests that different facial features' intensity varies in the way that they contribute to the recognition of the different facial expression intensity.
Basic Facial Expressions Analysis on a 3D Model: Based on Action Units and the Nose Tip
A 3D model with facial expressions as a platform to analyze the basic set of expressions and considered direction weighted intensity values of the FACS Action Units relative to the nose tip, serving as a reference point, to generate direction weighted score for each target expression.
3D Facial Action Units Recognition for Emotional Expression
It is consistent that AUs that are corresponded to sad expression has a high recognition compared to happy expression, and the highest average kernel performance across AUs is 93%, scored by quadratic kernel.
Quantification of Facial Movements of Healthy Individuals Using Viola-Jones and Otsu
This work quantifies four of the movements of the human face, lifting eyebrows, closing eyes, smiling and kissing, and identifies the tracking points (PS), with Viola-Jones and Otsu, within the thirds or fifths of the face, dependent on the movement.
3D Face Recognition Analysis Using Random Forest
The Random Forest approach to 3D facial recognition using the BU-3DFE database has yield 94.71% of recognition rate, which is an encouraging result compared to NN and SVM, and yields that fear expression is unique to each human due to a high confidence rate (82%) of subjects with fear expression.
Assessing Performance of Aerobic Routines using Background Subtraction and Intersected Image Region
A simple image similarity measure based on intersected image region to assess a subject's performance of an aerobic routine to reduce the risk of injury and maximise physical gains is presented.


Facial Expression Recognition Using 3D Facial Feature Distances
Facial expressions such as anger, sadness, surprise, joy, disgust, fear and neutral are successfully recognized with an average recognition rate of 91.3%, and the highest recognition rate reaches to 98.3% in the recognition of surprise.
3D facial expression classification using a statistical model of surface normals and a modular approach
A statistical model for variations in facial shape due to changes in six basic expressions using 3D facial surface normals as the feature vectors and a Weighted Voting Scheme (WVS) to infer the emotion underlying a collection of modules using a weight that is determined using the AdaBoost learning algorithm is constructed.
3D Facial Expression Recognition Based on Primitive Surface Feature Distribution
  • Jun Wang, L. Yin, Xiaozhou Wei, Yi Sun
  • Computer Science
    2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)
  • 2006
This paper proposes a novel approach to extract primitive 3D facial expression features, and then applies the feature distribution to classify the prototypic facial expressions, and demonstrates the advantages of the 3D geometric based approach over 2D texture based approaches in terms of various head poses.
3D facial expression recognition based on properties of line segments connecting facial feature points
  • Hao Tang, Thomas S. Huang
  • Computer Science
    2008 8th IEEE International Conference on Automatic Face & Gesture Recognition
  • 2008
This paper performs person and gender independent facial expression recognition based on properties of the line segments connecting certain 3D facial feature points, which comprises a set of 96 distinguishing features for recognizing six universal facial expressions.
Optimal feature selection for 3D facial expression recognition using coarse-to-fine classification
A feature selection process for pose-invariant 3D facial expression recognition is described, which provides a lower dimensional subspace representation, retrieved from geometrical localization of facial feature points to classify facial expressions.
A 3D facial expression database for facial behavior research
This is the first attempt at making a 3D facial expression database available for the research community, with the ultimate goal of fostering the research on affective computing and increasing the general understanding of facial behavior and the fine 3D structure inherent in human facial expressions.
Dynamic Facial Expression Analysis and Synthesis With MPEG-4 Facial Animation Parameters
A probabilistic framework for faithful reproduction of dynamic facial expressions on a synthetic face model with MPEG-4 facial animation parameters (FAPs) while achieving very low bitrate in data transmission.
Face Expression Recognition and Analysis: The State of the Art
A time-line view of the advances made in this field, the applications of automatic face expression recognizers, the characteristics of an ideal system, the databases that have been used and the advancesmade in terms of their standardization and a detailed summary of the state of the art are presented.
Facial areas and emotional information.
After two decades of scattered research, there has been a resurgence of interest in the predictability and measurement of facial expressions of emotion and the question of just where in the face one should look to find such information about emotion is renewed.
3 D Facial Expression Classification Using a Statistical Model of Surface Normals And a Modular Approach . eTheses Repository
  • 2012