自闭症儿童视觉特征数据库的构建与应用  

Construction and application of visual characteristics database for autistic children

作　　者：冉瑞生 邓姗 刘宸佚 梁伟 樊欣[2] RAN Ruisheng;DENG Shan;LIU Chenyi;LIANG Wei;FAN Xin(School of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China;Department of Pediatrics,Chongqing Maternal and Child Health Hospital)

机构地区：[1]重庆师范大学计算机与信息科学学院,重庆401331 [2]重庆市妇幼保健院儿保科

出　　处：《中国数字医学》2024年第4期105-115,共11页China Digital Medicine

基　　金：人工智能驱动下的自闭症儿童社会情绪评估研究(20YJAZH084)。

摘　　要：目的:由于儿童自闭症的隐私性,其数据集往往难以获取,这给相关的研究造成了一定的困难。为此,构建了自闭症儿童特征数据库。方法:首先设计交互场景,采集了一个自闭症儿童面部数据集,然后利用计算机视觉中的面部关键点检测、视线跟踪、头部姿态和面部动作单元等技术,提取自闭症儿童面部视觉特征,然后在提取的面部特征的基础上对所有特征数据进行编码,从而构建了一个自闭症儿童视觉特征数据库。结果:该视觉特征数据库可供该领域的研究人员使用。此外,基于该视觉特征库,本文以面部动作单元为例对自闭症儿童进行分析和预测,实验结果表明,分类精度最高可达93%。结论:该数据库可用于自闭症儿童的相关研究,具有较大的应用价值。Objective Due to the privacy of children with autism,their datasets are often difficult to obtain,which creates certain difficulties for related research.For this reason,this paper constructs a database of autistic children's characteristics.Methods Firstly,an interaction scene was designed and a facial dataset of children with autism was collected,and then facial visual features of children with autism were extracted using techniques of facial key point detection,line-of-sight tracking,head posture and facial action units in computer vision,and then all the feature data were encoded on the basis of the extracted facial features,so as to construct a database of visual features of children with autism.Results This visual feature database can be used by researchers in this field.In addition,based on this visual feature database,this paper analyzed and predicted children with autism using facial action units as an example,and the experimental results showed that the classification accuracy was up to 93%.Conclusion This database can be used in the research related to autistic children,and has a greater application value.

关 键 词：自闭症 计算机视觉 特征提取 数据库 临床辅助诊断 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] R319[自动化与计算机技术—计算机科学与技术]