摘要
本文系统分析了经典的和最新的局部二值模式人脸识别算法,结合基于特征的构件模型,设计了人脸识别软构件,并将构件应用到了人脸识别系统开发中.这些构件具有通用的接口和标准,能被不同的组织和个人用于二次开发,实现了软件的复用,减少了系统开发需要的成本.此外,本文还论述了将这些构件集成于人脸识别系统的方法,对比了集成于系统内的各种算法的识别性能.
This paper analyzed the classic and the latest face recognition algorithms based on local binary pattern. According to the characteristics of various algorithms and combing with feature—based component model,we designed software components for face recognition and applied these components to the development of face recognition system.These software components with a uniform interface and standard can be used by different organizations or individuals for secondary development,implementation of software reuse.Furthermore,the developed software components reduce the costs of secondary development and improve work efficiency.Besides, the paper also presented the method of assembling these components into an integrated system for face recognition. Finally,the recognition performance of various algorithms in the integrated system was compared.
出处
《微电子学与计算机》
CSCD
北大核心
2013年第5期43-46,共4页
Microelectronics & Computer
基金
国家自然科学基金项目(60971104)
四川省青年科技基金后续资助项目(09ZQ026-091)
高等学校博士学科点专项科研基金(20090184110008)
中国博士后科学基金(20110491736)
关键词
人脸识别
局部特征
软件复用
构件模型
系统集成
face recognition
local binary pattern
software reuse
component model
system integration
