A number of studies have revealed that eye size and symmetry were big factors of the attractiveness of a face. Each factor was investigated separately with no comparisons between themselves basing on the quality and quantity of each effect. In many articles, the "attractiveness" was used for explaining the importance of those factors from the viewpoint of evolutionary psychology. However, in some papers beauty and likability were used as a term of face preference. There has been little study to investigate these items simultaneously and the relations with the attractiveness. In this study, an experiment about beauty and likeability was conducted for the faces in which five types of eye sizes and symmetry were controlled, respectively. As the result, the largeness of the eye sizes increased the beauty/likeability of the face but extremely large eye lowered the evaluation value from the maximum. The highest rate of beauty/likeability was estimated at around 20% enlarged eyes of the intact eyes. On the other hand, the evaluation decreased monotonically according to the increase of the face asymmetry. By the comparison of the mean rating, there was no difference between beauty and likeability rating. From the analysis of the individual difference, however, it was clarified that some participants used the beauty and likeability in a different meaning. As the results showed consistent with that of the attractiveness, it suggested that other explanations not to be based on evolutionary psychology were necessary.
Available methods for synthesizing facial expressions synthesize basic expressions. Few methods synthesize subtle facial expressions such as a knavish smile or a cold smile. We developed a system for synthesizing subtle facial expressions. It uses an interactive interface based on a genetic algorithm. We use the five main parts of the face : eyebrows, eyes, mouth, and contours. These parts are deformed independently. Using this system, subtle facial expressions can be synthesized by iterating a deformation process for each part. Experiments showed that this system can efficiently synthesize subtle facial expressions.
In this paper, the effects of dynamic facial expression properties on the recognition of emotions were investigated. Although many studies of facial expression recognition and analysis have been conducted, the stimuli used in these experiments were typically static. Even when dynamic facial expressions were used, the experimental task was restricted to the basic expressions. In natural communication environments, facial expressions are often subtle or ambiguous. Studies of the analysis and synthesis of subtle and dynamic facial expressions are therefore required. As a quick going up expression could be recognized as a different emotion from a slow rising one, we represented facial expressions as the combination of time function of intensity and presentation speed. Experiments using stimuli that were combinations of four intensity time functions and three presentation speeds were conducted. Participants rated the perceived intensity of the emotions depicted, as well as how realistic they appeared to be. Time function and speed had different effects on different emotions, i.e. perceptions of anger were affected by set up speed, and the perceived intensity and realism of smiling expressions were also affected by speed.
Facial image retrieval problem is one of the typical example of information processing based on sensibility. The main reason is that the image retrieval problem has some difficulties about ambiguities of retrieval targets and non-determinateness of effective search-key. We propose a facial image retrieval system with the extended C4.5 algorithm as a retrieval mechanism. Some computer simulations are designed to investigate the performance of our system. The results of simulations represent that the our system shows good performance for the facial image retrieval problem.
