Human Reader: A Paradigm for a Multimedia-Based Human Interface

1995 ◽  
Vol 7 (3) ◽  
pp. 204-208 ◽  
Author(s):  
Yasuhito Suenaga ◽  
Keyword(s):  
Facial Expressions ◽  
Visual Information ◽  
Head Motion ◽  
Head Model ◽  
Model Generation ◽  
Head Direction ◽  
Research Projects ◽  
Human Interface ◽  
Face Images ◽  
3D Head Model

A paradigm for better human interface called Human Reader is introduced with references to computer vision (CV) and computer graphics (CG) research projects on human images at NTT Human Interface Laboratories. CV and CG are regarded as dual problems of visual information processing. Our research includes the recognition of face, detection of head direction and head motion, lip motion analysis, facial expressions analysis, detection of hand or finger positions and movements, 3D head model generation, synchronized acquisition of shape and color, and rendering realistic face images having various facial expressions with complex components such as hair.

3D head model generation using full-face head shape measurement system

2007 ◽  
Vol 38 (13) ◽  
pp. 82-91
Author(s):  
Takehiko Koyasu ◽  
Toshiyuki Amano ◽  
Yukio Sato
Keyword(s):  
Measurement System ◽  
Shape Measurement ◽  
Head Model ◽  
Model Generation ◽  
Head Shape ◽  
Full Face ◽  
3D Head Model

scholarly journals Hybrid Attention Cascade Network for Facial Expression Recognition

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2003 ◽  
Author(s):  
Xiaoliang Zhu ◽  
Shihao Ye ◽  
Liang Zhao ◽  
Zhicheng Dai
Keyword(s):  
Facial Expression ◽  
Facial Expressions ◽  
Facial Expression Recognition ◽  
Expression Recognition ◽  
Spatial Features ◽  
Face Images ◽  
Temporal Features ◽  
The Face ◽  
In The Wild ◽  
Fusion Features

As a sub-challenge of EmotiW (the Emotion Recognition in the Wild challenge), how to improve performance on the AFEW (Acted Facial Expressions in the wild) dataset is a popular benchmark for emotion recognition tasks with various constraints, including uneven illumination, head deflection, and facial posture. In this paper, we propose a convenient facial expression recognition cascade network comprising spatial feature extraction, hybrid attention, and temporal feature extraction. First, in a video sequence, faces in each frame are detected, and the corresponding face ROI (range of interest) is extracted to obtain the face images. Then, the face images in each frame are aligned based on the position information of the facial feature points in the images. Second, the aligned face images are input to the residual neural network to extract the spatial features of facial expressions corresponding to the face images. The spatial features are input to the hybrid attention module to obtain the fusion features of facial expressions. Finally, the fusion features are input in the gate control loop unit to extract the temporal features of facial expressions. The temporal features are input to the fully connected layer to classify and recognize facial expressions. Experiments using the CK+ (the extended Cohn Kanade), Oulu-CASIA (Institute of Automation, Chinese Academy of Sciences) and AFEW datasets obtained recognition accuracy rates of 98.46%, 87.31%, and 53.44%, respectively. This demonstrated that the proposed method achieves not only competitive performance comparable to state-of-the-art methods but also greater than 2% performance improvement on the AFEW dataset, proving the significant outperformance of facial expression recognition in the natural environment.

scholarly journals Do Valenced Odors and Trait Body Odor Disgust Affect Evaluation of Emotion in Dynamic Faces?

Perception ◽  
2017 ◽  
Vol 46 (12) ◽  
pp. 1412-1426 ◽  
Author(s):  
Elmeri Syrjänen ◽  
Marco Tullio Liuzza ◽  
Håkan Fischer ◽  
Jonas K. Olofsson
Keyword(s):  
Individual Differences ◽  
Facial Expressions ◽  
Visual Information ◽  
Relevant Information ◽  
Body Odor ◽  
Disgust Sensitivity ◽  
Facial Perception ◽  
Related Information ◽  
Dynamic Faces ◽  
Unpleasant Odor

Disgust is a core emotion evolved to detect and avoid the ingestion of poisonous food as well as the contact with pathogens and other harmful agents. Previous research has shown that multisensory presentation of olfactory and visual information may strengthen the processing of disgust-relevant information. However, it is not known whether these findings extend to dynamic facial stimuli that changes from neutral to emotionally expressive, or if individual differences in trait body odor disgust may influence the processing of disgust-related information. In this preregistered study, we tested whether a classification of dynamic facial expressions as happy or disgusted, and an emotional evaluation of these facial expressions, would be affected by individual differences in body odor disgust sensitivity, and by exposure to a sweat-like, negatively valenced odor (valeric acid), as compared with a soap-like, positively valenced odor (lilac essence) or a no-odor control. Using Bayesian hypothesis testing, we found evidence that odors do not affect recognition of emotion in dynamic faces even when body odor disgust sensitivity was used as moderator. However, an exploratory analysis suggested that an unpleasant odor context may cause faster RTs for faces, independent of their emotional expression. Our results further our understanding of the scope and limits of odor effects on facial perception affect and suggest further studies should focus on reproducibility, specifying experimental circumstances where odor effects on facial expressions may be present versus absent.

scholarly journals Transfer Entropy Based Causality From Head Motion To Eye Movement

2021 ◽  
Author(s):  
Zezhong Lv ◽  
Qing Xu ◽  
Klaus Schoeffmann ◽  
Simon Parkinson
Keyword(s):  
Eye Movement ◽  
Information Acquisition ◽  
Visual Information ◽  
Transfer Entropy ◽  
Movement Behavior ◽  
Head Motion ◽  
Human Beings ◽  
Sensorimotor Activity ◽  
Set Up ◽  
Psychophysical Studies

AbstractEye movement behavior, which provides the visual information acquisition and processing, plays an important role in performing sensorimotor tasks, such as driving, by human beings in everyday life. In the procedure of performing sensorimotor tasks, eye movement is contributed through a specific coordination of head and eye in gaze changes, with head motions preceding eye movements. Notably we believe that this coordination in essence indicates a kind of causality. In this paper, we investigate transfer entropy to set up a quantity for measuring an unidirectional causality from head motion to eye movement. A normalized version of the proposed measure, demonstrated by virtual reality based psychophysical studies, behaves very well as a proxy of driving performance, suggesting that quantitative exploitation of coordination of head and eye may be an effective behaviometric of sensorimotor activity.

Robust and discriminative dictionary learning for face recognition

2018 ◽  
Vol 16 (02) ◽  
pp. 1840004 ◽  
Author(s):  
Guojun Lin ◽  
Meng Yang ◽  
Linlin Shen ◽  
Mingzhong Yang ◽  
Mei Xie
Keyword(s):  
Face Recognition ◽  
Facial Expressions ◽  
Dictionary Learning ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Face Images ◽  
Proposed Model ◽  
Classification Capability ◽  
Discriminative Dictionary Learning

For face recognition, conventional dictionary learning (DL) methods have some disadvantages. First, face images of the same person vary with facial expressions and pose, illumination and disguises, so it is hard to obtain a robust dictionary for face recognition. Second, they don’t cover important components (e.g., particularity and disturbance) completely, which limit their performance. In the paper, we propose a novel robust and discriminative DL (RDDL) model. The proposed model uses sample diversities of the same face image to learn a robust dictionary, which includes class-specific dictionary atoms and disturbance dictionary atoms. These atoms can well represent the data from different classes. Discriminative regularizations on the dictionary and the representation coefficients are used to exploit discriminative information, which improves effectively the classification capability of the dictionary. The proposed RDDL is extensively evaluated on benchmark face image databases, and it shows superior performance to many state-of-the-art dictionary learning methods for face recognition.

Development of precise 3D head model : A sixteen million model

2003 ◽  
Vol VIII.03.1 (0) ◽  
pp. 95-96
Author(s):  
Tetsuya NISHIMOTO ◽  
Susumu EJIMA ◽  
Shigeyuki MURAKAMI ◽  
Hiroyuki TAKAO ◽  
Kohei TOMONAGA ◽  
...  
Keyword(s):  
Head Model ◽  
3D Head Model
Sign in / Sign up

Export Citation Format

Share Document