Local facial asymmetry for expression classification

Mitra, Sinjini; Liu, Yanxi

doi:10.1109/cvpr.2004.1315259

Cited by 43 publications

(27 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, it seems that facial actions involved in spontaneous emotional expressions are more symmetrical, involving both the left and the right side of the face, than deliberate actions displayed on request [31]. Based upon these observations, Mitra and Liu [32] have shown that facial asymmetry has sufficient discriminating power to improve the performance of an automated emotion classifier significantly. Martinez [33] has shown that, by taking into account facial asymmetry caused by certain emotion, expression-invariant face recognition can be achieved.…”

Section: Automated Facs: Profile Facementioning

confidence: 99%

Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences

Pantić

Patras

2006

IEEE Trans. Syst., Man, Cybern. B

478

283

View full text Add to dashboard Cite

Abstract-Automatic analysis of human facial expression is a challenging problem with many applications. Most of the existing automated systems for facial expression analysis attempt to recognize a few prototypic emotional expressions, such as anger and happiness. Instead of representing another approach to machine analysis of prototypic facial expressions of emotion, the method presented in this paper attempts to handle a large range of human facial behavior by recognizing facial muscle actions that produce expressions. Virtually all of the existing vision systems for facial muscle action detection deal only with frontal-view face images and cannot handle temporal dynamics of facial actions. In this paper, we present a system for automatic recognition of facial action units (AUs) and their temporal models from long, profile-view face image sequences. We exploit particle filtering to track 15 facial points in an input face-profile sequence, and we introduce facial-action-dynamics recognition from continuous video input using temporal rules. The algorithm performs both automatic segmentation of an input video into facial expressions pictured and recognition of temporal segments (i.e., onset, apex, offset) of 27 AUs occurring alone or in a combination in the input face-profile video. A recognition rate of 87% is achieved.

show abstract

Section: Automated Facs: Profile Facementioning

confidence: 99%

Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences

Pantić

Patras

2006

IEEE Trans. Syst., Man, Cybern. B

478

283

View full text Add to dashboard Cite

show abstract

“…[3,10,17,19,20,24,30,31,35,37]). Symmetry detection has been used for numerous applications, including facial image analysis [23], vehicle detection [12,38], reconstruction [1,6,14,34], visual attention [17,24,27] indexing of image databases [28], completion of occluded shapes [36], object detection [19,37] and detecting tumours in medical imaging [18]. The problem of symmetry detection amounts to trying to find an image region of unknown size that, when flipped about an unknown axis or rotated about an unknown point, is sufficiently similar to another image region an unknown distance away.…”

Section: Introductionmentioning

confidence: 99%

Detecting Symmetry and Symmetric Constellations of Features

Loy

Eklundh

2006

Lecture Notes in Computer Science

270

428

View full text Add to dashboard Cite

Abstract.A novel and efficient method is presented for grouping feature points on the basis of their underlying symmetry and characterising the symmetries present in an image. We show how symmetric pairs of features can be efficiently detected, how the symmetry bonding each pair is extracted and evaluated, and how these can be grouped into symmetric constellations that specify the dominant symmetries present in the image. Symmetries over all orientations and radii are considered simultaneously, and the method is able to detect local or global symmetries, locate symmetric figures in complex backgrounds, detect bilateral or rotational symmetry, and detect multiple incidences of symmetry.

show abstract

“…After considering many approaches such as Bayesian, Heuristic, Expert systems, Markov, Self-organising map and Artificial Neural Networks (ANNs), to deal even with nonlinear discrimination between classes and to accept incomplete or ambiguous input patterns, Mitra and Liu (8) state that existing approaches generally tend to suffer from problems that result from high sensitivity to noise included in the data and unreliability in dealing with new or ambiguous patterns.…”

Section: Literature Reviewmentioning

confidence: 99%

Cardiology Predictor: Cardiology Interpretations for Medical Diagnosis

Nallaperuma

Lokuge

2012

Sri Lanka J Bio-Medical Informatics

View full text Add to dashboard Cite

Diagnosis of a heart disease is complex. Aspects such as clinical details, blood pressure, pulse rate, cholesterol level and blood test reports, and even patient"s history, gender and age all are important when diagnosing cardiovascular disease. Interpretation of an Elector Cardiogram (ECG) is one of a key skill developed by cardiologists. Difficulties in analysing complicated ECG may lead to inaccurate diagnosis thus affecting the accuracy and quality with the diagnosis of cardiovascular disease especially among novice."Cardiology Predictor" is a software system which is capable of assisting medical practitioners to diagnose cardiovascular diseases accurately. The inputs to the system would be ECG and other cardiac factors which would be processed to provide an output of the possible cardiovascular disease. To ensure accuracy and efficiency, ECG signals are used with digital signal processing for decrypting and feature extracting. Furthermore, artificial intelligence is used to diagnose cardiovascular diseases due to the complexity embedded into it. Therefore, an Artificial Neural Network was used to predict cardiovascular disease. The average success rate of the system was 85.6% based on the user evaluation. Domain experts such as cardiologists suggested that the system is most suitable for the emergency room where expert knowledge was not readily available.

show abstract

Local facial asymmetry for expression classification

Cited by 43 publications

References 18 publications

Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences

Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences

Detecting Symmetry and Symmetric Constellations of Features

Cardiology Predictor: Cardiology Interpretations for Medical Diagnosis

Contact Info

Product

Resources

About