A facial expression image database and norm for Asian population: a preliminary report

Chen, Chien‐Chung; Cho, Shu Ling; Horszowska, Katarzyna; Chen, Mei Yen; Wu, Chia-Ching; Chen, Hsueh Chih; Yeh, Yi Yu; Cheng, Chao

doi:10.1117/12.806130

Cited by 13 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of 336 face expressions of eight category are selected from TFEID ( Taiwanese facial Expression Image Database) [26] . Query images are selected at random from the test database.…”

Section: Results Analysismentioning

confidence: 99%

Multi-Query Content Based Image Retrieval System using Local Binary Patterns

Joseph¹,

Balakrishnan²

2011

IJCA

View full text Add to dashboard Cite

Content Based Image Retrieval systems open new research areas in Computer Vision due to the high demand of image searching methods. CBIR is the process of finding relevant image from large collection of images using visual queries. The proposed system uses multiple image queries for finding desired images from database. The different queries are connected using logical AND operation. Local Binary Pattern (LBP) texture descriptors of the query images are extracted and those features are compared with the features of the images in the database for finding the desired images. The proposed system is used for retrieving similar human face expressions. The use of multiple queries reduces the semantic gap between low level visual features and high level user expectation. The experimental result shows that, the use of multiple queries has better retrieval performance over single image queries.

show abstract

“…A total of 336 face expressions of eight category are selected from TFEID ( Taiwanese facial Expression Image Database) [26] . Query images are selected at random from the test database.…”

Section: Results Analysismentioning

confidence: 99%

Multi-Query Content Based Image Retrieval System using Local Binary Patterns

Joseph¹,

Balakrishnan²

2011

IJCA

View full text Add to dashboard Cite

show abstract

“…To ensure and motivate our subjects in the performance of this task, actual monetary rewards were applied to mimic real-life events. Three types of facial expressions from the culture-based facial-expression database (Chen et al, 2009 , 2013 ) were selected to prime affective arousal in each group. Patterns on the PANAS and facial-expression ratings evidenced that facial primes were perceived by our subjects and successfully elicited corresponding affective arousal as planned, and this was further confirmed by the N170 and EEP results.…”

Section: Discussionmentioning

confidence: 99%

“…A split-plot design was adopted here. Subjects were randomly assigned into one of the three groups, and were exposed to one of the three types of facial expressions (i.e., happy, angry, and neutral faces) from the database (Chen et al, 2009 , 2013 ) prior to choosing the card in each trial. Subjects in the AN (and HN, respectively) group were randomly exposed to angry (and happy, respectively) faces (as the affective prime) in half of the trials and to neutral faces (as the neutral prime) in the other half of the trials (Figure 1D ).…”

Section: Methodsmentioning

confidence: 99%

“…The NN group served as the group-wise baseline control and the neutral condition in the AN and HN groups served as the within-subject baseline control. Three types of facial expressions (i.e., neutral, angry, and happy faces) from a culture-based facial-expression database (Chen et al, 2009 , 2013 ) were selected to elicit affective arousal for each corresponding group. Specifically, angry and happy faces were adopted as the affective primes and neutral faces were used as the neutral prime.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Effects of affective arousal on choice behavior, reward prediction errors, and feedback-related negativities in human reward-based decision making

et al. 2015

View full text Add to dashboard Cite

Emotional experience has a pervasive impact on choice behavior, yet the underlying mechanism remains unclear. Introducing facial-expression primes into a probabilistic learning task, we investigated how affective arousal regulates reward-related choice based on behavioral, model fitting, and feedback-related negativity (FRN) data. Sixty-six paid subjects were randomly assigned to the Neutral-Neutral (NN), Angry-Neutral (AN), and Happy-Neutral (HN) groups. A total of 960 trials were conducted. Subjects in each group were randomly exposed to half trials of the pre-determined emotional faces and another half of the neutral faces before choosing between two cards drawn from two decks with different assigned reward probabilities. Trial-by-trial data were fit with a standard reinforcement learning model using the Bayesian estimation approach. The temporal dynamics of brain activity were simultaneously recorded and analyzed using event-related potentials. Our analyses revealed that subjects in the NN group gained more reward values than those in the other two groups; they also exhibited comparatively differential estimated model-parameter values for reward prediction errors. Computing the difference wave of FRNs in reward vs. non-reward trials, we found that, compared to the NN group, subjects in the AN and HN groups had larger “General” FRNs (i.e., FRNs in no-reward trials minus FRNs in reward trials) and “Expected” FRNs (i.e., FRNs in expected reward-omission trials minus FRNs in expected reward-delivery trials), indicating an interruption in predicting reward. Further, both AN and HN groups appeared to be more sensitive to negative outcomes than the NN group. Collectively, our study suggests that affective arousal negatively regulates reward-related choice, probably through overweighting with negative feedback.

show abstract

“…Some may argue that such simplification may fail in certain parts of a face, such as the eyebrows and eye details that have a different coloration from the skin. However, we computed the size of these details for 76 faces from a database [26] and found that these features combined occupied only about 3% area of the face. Hence, for a face model with no highlights, the product of C and L in the interaction term in Eq 2 can be treated as negligible for our stimuli.…”

Section: Introductionmentioning

confidence: 99%

Depth Structure from Asymmetric Shading Supports Face Discrimination

Chen

Chen²,

Tyler³

2013

PLoS ONE

Self Cite

View full text Add to dashboard Cite

To examine the effect of illumination direction on the ability of observers to discriminate between faces, we manipulated the direction of illumination on scanned 3D face models. In order to dissociate the surface reflectance and illumination components of front-view face images, we introduce a symmetry algorithm that can separate the symmetric and asymmetric components of the face in both low and high spatial frequency bands. Based on this approach, hybrid faces stimuli were constructed with different combinations of symmetric and asymmetric spatial content. Discrimination results with these images showed that asymmetric illumination information biased face perception toward the structure of the shading component, while the symmetric illumination information had little, if any, effect. Measures of perceived depth showed that this property increased systematically with the asymmetric but not the symmetric low spatial frequency component. Together, these results suggest that (1) the asymmetric 3D shading information dramatically affects both the perceived facial information and the perceived depth of the facial structure; and (2) these effects both increase as the illumination direction is shifted to the side. Thus, our results support the hypothesis that face processing has a strong 3D component.

show abstract

A facial expression image database and norm for Asian population: a preliminary report

Cited by 13 publications

References 20 publications

Multi-Query Content Based Image Retrieval System using Local Binary Patterns

Multi-Query Content Based Image Retrieval System using Local Binary Patterns

Effects of affective arousal on choice behavior, reward prediction errors, and feedback-related negativities in human reward-based decision making

Depth Structure from Asymmetric Shading Supports Face Discrimination

Contact Info

Product

Resources

About