{"title":"Head movement analysis in lie detection","authors":"Dora-Ionut Noje, R. Malutan","doi":"10.1109/ROLCG.2015.7367432","DOIUrl":null,"url":null,"abstract":"This document presents a study regarding the potential of head movement in lie detection. The potential was analyzed using a non-invasive technique that detects the head movement out of video. In the literature there is a lot of information regarding lie indicators and for this reason we made a short review of them. Application was built in order to detect the head movement and head position by performing a frame-to-frame analysis on a color video stream. Tests were performed on a group of ten volunteers and the results confirmed the theory. A correlation was made between head movement/ position and lie detection. Although the results confirmed the theory they are not concluding because this information cannot be used without other additional information from the other information channels like voice, words, gaze and so on. User must correlate the responses of the suspects with the response of the application in order to decide what the verdict is.","PeriodicalId":126559,"journal":{"name":"2015 Conference Grid, Cloud & High Performance Computing in Science (ROLCG)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 Conference Grid, Cloud & High Performance Computing in Science (ROLCG)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROLCG.2015.7367432","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
This document presents a study regarding the potential of head movement in lie detection. The potential was analyzed using a non-invasive technique that detects the head movement out of video. In the literature there is a lot of information regarding lie indicators and for this reason we made a short review of them. Application was built in order to detect the head movement and head position by performing a frame-to-frame analysis on a color video stream. Tests were performed on a group of ten volunteers and the results confirmed the theory. A correlation was made between head movement/ position and lie detection. Although the results confirmed the theory they are not concluding because this information cannot be used without other additional information from the other information channels like voice, words, gaze and so on. User must correlate the responses of the suspects with the response of the application in order to decide what the verdict is.