摘要
针对用于移动设备的生物特征识别多模态融合技术框架不统一以及标准缺失的问题,提出了多模态融合的分类、层级以及标准统一技术框架。首先分析国内外与移动设备生物特征识别相关的标准化现状;其次研究移动设备生物特征识别标准的本地识别以及远程识别应用模式,分析提出多特征、多算法、多实例、多传感器4种多模态融合分类方法,研究并提出样本级融合、特征级融合、分数级融合和决策级融合4种多模态融合的层级,并且提出用于移动设备的生物特征识别多模态融合标准技术框架;最后对移动设备生物特征识别多模态融合技术应用进行展望。
Aiming at the problem of inconsistent biometric multi-modal fusion technology framework for mobile devices and lack of standards,a unified technical framework of multi-modal fusion standards was proposed.Firstly,the current status of standardization related to biometric used with mobile device was analyzed.Secondly,the local recognition and remote recognition application modes of mobile device biometrics standards were studied,and then four sub-multimodal fusion classification methods of multi-feature,multi-algorithm,multi-instance,and multi-sensor were analyzed and proposed.Then,four levels of multi-modal fusion were researched and proposed:sample-level fusion,feature-level fusion,score-level fusion,and decision-level fusion,and a standard technical framework for biometric multi-modal fusion for mobile devices was proposed.Finally,prospects for the application of biometric multi-modal fusion technology were given.
作者
林冠辰
王智飞
LIN Guanchen;WANG Zhifei(Ant Group Co.,Ltd.,Beijing 100004,China;Information Centre,Ministry of Human Resources and Social Security,Beijing 100013,China)
出处
《电信科学》
2021年第1期32-38,共7页
Telecommunications Science
基金
国家重点研发计划基金资助项目(No.2018YFF0213004)。