Robust Shape-Based Head Tracking

Hou, Yanze; Sahli, Hichem; Ravyse, Ilse; Zhang, Yanning; Zhao, Ran

doi:10.1007/978-3-540-74607-2_31

Cited by 17 publications

(9 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The head and facial feature were tracked using the Constrained Shape Tracking approach of [17]. This approach allows an automatic detection of the head and the tracking of a shape model composed of 83 facial landmarks, located as illustrated in Fig.…”

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of facial actions and their temporal segments based on duration models

González

Cartella

Enescu

et al. 2014

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Being able to automatically analyze finegrained changes in facial expression into action units (AUs), of the Facial Action Coding System (FACS), and their temporal models (i.e., sequences of temporal phases, neutral, onset, apex, and offset), in face videos would greatly benefit for facial expression recognition systems. Previous works, considered combining, per AU, a discriminative frame-based Support Vector Machine (SVM) and a dynamic generative Hidden Markov Models (HMM), to detect the presence of the AU in question and its temporal segments in an input image sequence. The major drawback of HMMs, is that they do not model well time dependent dynamics as the ones of AUs, especially when dealing with spontaneous expressions. To alleviate this problem, in this paper, we exploit efficient duration modeling of the temporal behavior of AUs, and we propose hidden semi-Markov model (HSMM) and variable duration semi-Markov model (VDHMM) to recognize the dynamics of AU's. Such models allow the parameterization and inference of the AU's state duration distributions. Within our system, geometrical and appearance based measurements, as well as their first derivatives, modeling both the dynamics and the appearance of AUs, are applied to pair-wise SVM classifiers for a frame-based classification. The output of which are then fed as evidence to the HSMM or VDHMM for inferring AUs temporal phases. A thorough investigation into the aspect of duration modeling and its application to AU recognition through extensive comparison to state-of-art SVM-HMM approaches are presented. For comparison, an average recognition rate of 64.83 % and 64.66 % is achieved for the HSMM and VDHMM respectively. Our framework has several benefits: (1) it models the AU's temporal phases duration; (2) it does not require any Multimed Tools Appl assumption about the underlying structure of the AU events, and (3) compared to HMM, the proposed HSMM and VDHMM duration models reduce the duration error of the temporal phases of an AU, and they are especially better in recognizing the offset ending of an AU.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

“…As discussed in Section 3.1, the input to the HMM are the emission probabilities obtained using (17). Hence, the observation at time t is defined as a vector of 4 components as…”

Section: The State Transition Probability Distributionmentioning

confidence: 99%

Recognition of facial actions and their temporal segments based on duration models

González

Cartella

Enescu

et al. 2014

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this work, we adopt the constrained Bayesian tangent shape model (CSM) algorithm [16] to detect and track a shape model defined by 83 facial landmarks. Fig.1 In [13], an 8-dimensional feature vector, describing the movements of eyes and eyebrows in the upper face, has been used.…”

Section: D Facial Featuresmentioning

confidence: 99%

Audio Visual Emotion Recognition Based on Triple-Stream Dynamic Bayesian Network Models

Jiang

Cui

Zhang

et al. 2011

Affective Computing and Intelligent Interaction

Self Cite

View full text Add to dashboard Cite

Abstract. We present a triple stream DBN model (T_AsyDBN) for audio visual emotion recognition, in which the two audio feature streams are synchronous, while they are asynchronous with the visual feature stream within controllable constraints. MFCC features and the principle component analysis (PCA) coefficients of local prosodic features are used for the audio streams. For the visual stream, 2D facial features as well 3D facial animation unit features are defined and concatenated, and the feature dimensions are reduced by PCA. Emotion recognition experiments on the eNERFACE'05 database show that by adjusting the asynchrony constraint, the proposed T_AsyDBN model obtains 18.73% higher correction rate than the traditional multi-stream state synchronous HMM (MSHMM), and 10.21% higher than the two stream asynchronous DBN model (Asy_DBN).

show abstract

“…Our features are geometry, and consist of a shape model of 83 facial feature points [6], see Figure 1. Once we have the shape model for all video frames, we apply an affine transformation by warping each image to a common view.…”

Section: Feature Extractionmentioning

confidence: 99%