节点文献

人脸自动识别技术的研究与实现

Research and Implementation of the Technology of Automatic Human Face Recognition

【作者】 王德新

【导师】 徐全生;

【作者基本信息】 沈阳工业大学 , 计算机应用技术, 2004, 硕士

【摘要】 随着社会的发展,信息化程度的不断提高,各个方面对快速有效的自动身份验证的要求日益迫切。由于生物特征是人的内在属性,具有很强的自身稳定性和个体差异性,因此它是身份验证的最理想依据。利用人脸特征进行身份验证又是最自然直接的手段,人脸相比其它人体生物特征它具有直接、友好、方便的特点,由此人脸自动识别成为身份验证的研究热点。 人脸识别技术有着广泛的应用背景。人脸自动识别系统可应用于公安系统的罪犯身份识别、驾驶执照及护照等证件照片与实际持证人的核对、银行及海关的监控系统及一些保密单位的自动门卫系统等。此外,人脸识别技术在信息安全领域也有着巨大的潜在应用价值。可以进行计算机的安全登录控制、应用程序安全使用、数据库安全访问和文件加密,还可以保护电子商务的安全性,还可用于图像库检索,在大型人脸库中检索与索引图像相同或相近的脸像。美国遭遇恐怖袭击后,这一技术引起更广泛关注。作为最容易隐蔽使用的识别技术,人脸识别成为当今国际反恐和安全防范最重要的手段之一。 本课题主要研究目标是人脸自动识别系统的实现。人脸自动识别系统包括人脸的检测、特征提取、人脸识别三个部分。人脸的检测和定位,即首先从输入图像中找到人脸及人脸存在的位置,并将人脸从背景中分割出来;然后对归一化的人脸图像进行特征提取,有效的抽取识别特征是人脸识别的关键;最后,进行人脸识别。人脸识别是指对给定的包含人脸的输入图像,通过与已知人脸库中存储的模型进行匹配比较,确定是否是库中某一人物,如果是,则给出最佳匹配库中人物。就可以实现自动识别人脸的目的。

【Abstract】 With the development of society and the degree of society information improving rapidly, in all aspects the demand for effective automatic identity verification is increasingly urgent. The biological characteristics are the human inherent attributes, which have very strong stability and individual difference, so it is the most ideal basis of identity verification. Make use of the human face characteristics to carry on the identity verification is the most natural and direct means, Comparing with other the human biological characteristics it has direct, friendly and convenient characteristics, therefore automatic human face recognition becomes the research focus of the identity verification.Human face recognition technology has extensive application backgrounds. Automatic human face recognition system can be applied for criminal identity verification of public security system, check certificate photo with holder , such as driving license and passport ,etc, and the Monitoring system of bank and the customs and the automatic entrance guard systems etc. In addition, human face recognition technology has enormous potential application value in the field of information safety. Human face recognition technology can carry on security log-in controlling, application program using safely, database visiting safely and file encryption of the computer. It can also protect the security of e-commerce, and search the picture storehouse, searching the same as or close face among large-scale human face storehouse. After American is attacked by terrorists, this technology causes more extensive concern. As an easy concealing recognition technology, human face recognition nowadaysbecomes international anti-terrorism and one of the most important means of safe precaution. The main goal of this subject is realization of the automatic human face recognition system.The automatic human face recognition system includes face detection, feature extraction and face recognition, face location and face detection at first find human face and the position from inputting picture in face storehouse, cut apart human face from the background; Then human face picture in normalization carry on feature extraction. Effectively extracting recognition feature is the key of human face recognition; finally, carrying on the face recognition. To givingthe introduction picture which includes the human faces human face recognition technology is compared with and match known human face model that stored in the face storehouse, confirming whether it is one person in the storehouse or not, if yes, providing the best matching person in the storehouse can realize the purpose of human face recognition automatically.

  • 【分类号】TP391.41
  • 【被引频次】2
  • 【下载频次】525
节点文献中: