中文摘要 |
本研究收集29位專業表演者以表演、Ekman表情肌肉變動形式及生活感受三種表現方式,在正面、3/4側面、側面所呈現之七種臉部表情,獲得12,393張有效影像檔案,以建立華人族群情緒臉影像資料庫及常模。七種表情情緒分別為:快樂、生氣、悲傷、厭惡、害怕、驚訝及平靜表情。有效影像檔案中,最具代表性的臉孔影像,1,232張為正面情緒臉影像,514張3/4側臉影像,527張側面臉影像。由400名大學生評定正面臉孔,200名大學生評定3/4臉孔,50名大學生評定側面臉孔,每一參與者皆針對臉孔進行六種表情類型之強度判斷。另為落實本土化實證研究,採用專業表演者與評定人員均為華人背景,也因此本研究所獲得之情緒表情資料庫可用於涉及文化背景議題之情緒研究。 |
英文摘要 |
To establish an image database and norm for facial expression in local population, we collected 12,393 valid images from 29 professional performers in facial expression of seven basic emotions: happiness, anger, sadness, disgust, fear, surprise, and neutral. Among them, the most representative 1,232 frontal view, 514 3/4 view and 527 profile images from all models were each rated by 50 ~ 100 human observers for the category and intensity of perceived emotion. Such large number of emotion categories, models and raters should be sufficient for most serious expression recognition research both in psychology and in computer science. All the models and raters are of Asian background. Hence, this database can also be used when the culture background is a concern. |