{"title":"基于 Haar Cascade 的人脸识别三宝垄航空员工在岗系统","authors":"Fidela Azzahra, C. A. Sari, E. H. Rachmawanto","doi":"10.26877/asset.v6i3.672","DOIUrl":null,"url":null,"abstract":"The presence of employees is a key factor in supporting the needs of the workplace. At present, the employee presence system at PT. AirNav Indonesia Semarang Branch still uses fingerprint and RFID-based employee ID cards for authentication. This RFID-based system can increase employee fraud by allowing employees to misuse each other's ID cards. To avoid such fraud, a system needs to be built and it will be using face recognition technology as the primary authentication method, with the Haar Cascade Algorithm. This algorithm has the advantage of being computationally fast, as it only relies on the number of pixels within a rectangle, not every pixel of an image. In addition to fast computation, this algorithm also has the advantage of identifying objects that are relatively far away. With the implementation of the Haar Cascade algorithm, the results indicate the capability of face recognition in detecting the faces of registered employees within the system based on facial angles with an accuracy rate of 60%, expressions with an accuracy rate of 100%, as well as obstructive parameters such as glasses and masks with an accuracy rate of 33.33%. The ability to detect objects from various camera angles, recognize faces with different expressions, and identify objects obstructed by parameters can serve as reasons why this algorithm needs to be implemented","PeriodicalId":414022,"journal":{"name":"Advance Sustainable Science Engineering and Technology","volume":"3 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"The AirNav Semarang Employee Presence System Using Face Recognition Based on Haar Cascade\",\"authors\":\"Fidela Azzahra, C. A. Sari, E. H. Rachmawanto\",\"doi\":\"10.26877/asset.v6i3.672\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The presence of employees is a key factor in supporting the needs of the workplace. At present, the employee presence system at PT. AirNav Indonesia Semarang Branch still uses fingerprint and RFID-based employee ID cards for authentication. This RFID-based system can increase employee fraud by allowing employees to misuse each other's ID cards. To avoid such fraud, a system needs to be built and it will be using face recognition technology as the primary authentication method, with the Haar Cascade Algorithm. This algorithm has the advantage of being computationally fast, as it only relies on the number of pixels within a rectangle, not every pixel of an image. In addition to fast computation, this algorithm also has the advantage of identifying objects that are relatively far away. With the implementation of the Haar Cascade algorithm, the results indicate the capability of face recognition in detecting the faces of registered employees within the system based on facial angles with an accuracy rate of 60%, expressions with an accuracy rate of 100%, as well as obstructive parameters such as glasses and masks with an accuracy rate of 33.33%. The ability to detect objects from various camera angles, recognize faces with different expressions, and identify objects obstructed by parameters can serve as reasons why this algorithm needs to be implemented\",\"PeriodicalId\":414022,\"journal\":{\"name\":\"Advance Sustainable Science Engineering and Technology\",\"volume\":\"3 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advance Sustainable Science Engineering and Technology\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.26877/asset.v6i3.672\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advance Sustainable Science Engineering and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26877/asset.v6i3.672","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
员工在场是支持工作场所需求的一个关键因素。目前,PT.AirNav Indonesia Semarang 分公司的员工到岗系统仍使用指纹和基于 RFID 的员工 ID 卡进行身份验证。这种基于 RFID 的系统可能会允许员工滥用彼此的身份证,从而增加员工欺诈行为。为了避免这种欺诈行为,需要建立一个系统,该系统将使用人脸识别技术作为主要的身份验证方法,并采用 Haar Cascade 算法。这种算法的优点是计算速度快,因为它只依赖于矩形内的像素数量,而不是图像的每个像素。除了计算速度快之外,这种算法还具有识别相对较远物体的优势。在采用 Haar Cascade 算法后,结果表明,人脸识别技术能够根据面部角度检测系统内注册员工的脸部,准确率为 60%;根据表情检测的准确率为 100%;根据眼镜和面具等障碍参数检测的准确率为 33.33%。从不同的摄像机角度检测物体、识别不同表情的人脸以及识别受参数阻碍的物体的能力,可以作为需要实施该算法的理由
The AirNav Semarang Employee Presence System Using Face Recognition Based on Haar Cascade
The presence of employees is a key factor in supporting the needs of the workplace. At present, the employee presence system at PT. AirNav Indonesia Semarang Branch still uses fingerprint and RFID-based employee ID cards for authentication. This RFID-based system can increase employee fraud by allowing employees to misuse each other's ID cards. To avoid such fraud, a system needs to be built and it will be using face recognition technology as the primary authentication method, with the Haar Cascade Algorithm. This algorithm has the advantage of being computationally fast, as it only relies on the number of pixels within a rectangle, not every pixel of an image. In addition to fast computation, this algorithm also has the advantage of identifying objects that are relatively far away. With the implementation of the Haar Cascade algorithm, the results indicate the capability of face recognition in detecting the faces of registered employees within the system based on facial angles with an accuracy rate of 60%, expressions with an accuracy rate of 100%, as well as obstructive parameters such as glasses and masks with an accuracy rate of 33.33%. The ability to detect objects from various camera angles, recognize faces with different expressions, and identify objects obstructed by parameters can serve as reasons why this algorithm needs to be implemented