作者: Zhang Keke , Teng Wendi , Zheng Yaona , Yu Zixi , Sun Xiao
DOI:
关键词: Binary number 、 Histogram 、 Pattern recognition 、 Computer science 、 Image (mathematics) 、 Artificial intelligence 、 Identification rate 、 Fusion 、 Expression (mathematics) 、 Facial expression 、 Identification (information)
摘要: The invention discloses a monogenic multi-characteristic face expression identification method based on sparse fusion. comprises the following steps of: 1, carrying out filtering an image after pre-processing, and obtaining amplitude information, direction phase transverse conversion information longitudinal in three dimensions; 2, utilizing five kinds of to extract binary mode histogram characteristic, characteristic image, wherein characteristics respectively construct corresponding dictionaries; 3, l1 regularization least square optimize weights dictionaries, realizing by means weighted According invention, texture, shape can be fully extracted, rate is improved.