广州大学学报(自然科学版)
廣州大學學報(自然科學版)
엄주대학학보(자연과학판)
Journal of Guangzhou University (Natural Science Edition)
2015年
5期
67-70
,共4页
三维建模%单训练样本%视频监控%PCA%LDA
三維建模%單訓練樣本%視頻鑑控%PCA%LDA
삼유건모%단훈련양본%시빈감공%PCA%LDA
3D modeling%single training sample%video surveillance%PCA%LDA
近年来视频监控已普遍应用于各行各业,因此基于监控视频人脸识别也成为了智能监控系统中重要的研究领域。然而,由于监控视频人脸通常是非正面人脸,传统性能优良算法应用于视频人脸识别时,其性能也明显降低。同时,单张训练人脸问题在监控视频人脸检测和识别是一个普遍问题。因此为了能有效地提高单训练多姿态人脸识别的正确识别率,文章提出了一种基于三维建模技术的人脸识别算法。该算法先由一张二维高清正面人脸生成一个三维人脸模型,然后再进一步在该三维人脸空间里产生多种姿态的人脸模型,并由此获得多张相应姿态下的二维虚拟人脸,最后利用原始正面样本和所得到的虚拟人脸来构筑训练人脸库。该算法用SCface 视频监控人脸库中加以验证,与传统的 PCA 和 LDA 算法相比,该算法对监控视频人脸的识别率提高了13%。由此表明,文章介绍的算法是一种有效的人脸识别算法,能有效地提高对俯视人脸的识别率。
近年來視頻鑑控已普遍應用于各行各業,因此基于鑑控視頻人臉識彆也成為瞭智能鑑控繫統中重要的研究領域。然而,由于鑑控視頻人臉通常是非正麵人臉,傳統性能優良算法應用于視頻人臉識彆時,其性能也明顯降低。同時,單張訓練人臉問題在鑑控視頻人臉檢測和識彆是一箇普遍問題。因此為瞭能有效地提高單訓練多姿態人臉識彆的正確識彆率,文章提齣瞭一種基于三維建模技術的人臉識彆算法。該算法先由一張二維高清正麵人臉生成一箇三維人臉模型,然後再進一步在該三維人臉空間裏產生多種姿態的人臉模型,併由此穫得多張相應姿態下的二維虛擬人臉,最後利用原始正麵樣本和所得到的虛擬人臉來構築訓練人臉庫。該算法用SCface 視頻鑑控人臉庫中加以驗證,與傳統的 PCA 和 LDA 算法相比,該算法對鑑控視頻人臉的識彆率提高瞭13%。由此錶明,文章介紹的算法是一種有效的人臉識彆算法,能有效地提高對俯視人臉的識彆率。
근년래시빈감공이보편응용우각행각업,인차기우감공시빈인검식별야성위료지능감공계통중중요적연구영역。연이,유우감공시빈인검통상시비정면인검,전통성능우량산법응용우시빈인검식별시,기성능야명현강저。동시,단장훈련인검문제재감공시빈인검검측화식별시일개보편문제。인차위료능유효지제고단훈련다자태인검식별적정학식별솔,문장제출료일충기우삼유건모기술적인검식별산법。해산법선유일장이유고청정면인검생성일개삼유인검모형,연후재진일보재해삼유인검공간리산생다충자태적인검모형,병유차획득다장상응자태하적이유허의인검,최후이용원시정면양본화소득도적허의인검래구축훈련인검고。해산법용SCface 시빈감공인검고중가이험증,여전통적 PCA 화 LDA 산법상비,해산법대감공시빈인검적식별솔제고료13%。유차표명,문장개소적산법시일충유효적인검식별산법,능유효지제고대부시인검적식별솔。
Video surveillance has more and more been applied in recent years for security,video-based face recognition therefore became an important task in intelligence monitoring system.However,among these cap-tured video faces there are many non-frontal faces.As a result the art of state algorithms would become worse. On the other hand,only one training sample could usually be got.In order to effectively improve the correct rec-ognition rate of multi-pose face recognition with single frontal training sample,this paper proposed a face recog-nition algorithm based on 3D modelling.In the proposed algorithm,firstly a 2D frontal face with high-resolution was taken to build a 3D face model,and then several virtual faces with different poses were produced from the 3D face model.At last,both the original frontal face image and virtual face images were put into gallery set. The algorithm was evaluated on SCface database using traditional PCA and LDA methods.The result showed that the proposed approach could effectively improve recognition rate of looking-down faces.