Selected Papers from the 1st International Conference on Islam, Science and Technology, ICONISTECH-1 2019, 11-12 July 2019, Bandung, Indonesia

Research Article

Face Recognition Application Using Adaptive Boosting and Gray Level Co-Occurrence Matrix

Download412 downloads
  • @INPROCEEDINGS{10.4108/eai.11-7-2019.2297826,
        author={Chairisni  Lubis and Novario Jaya Perdana and Hengki  Pranoto},
        title={Face Recognition Application Using Adaptive Boosting and Gray Level Co-Occurrence Matrix},
        proceedings={Selected Papers from the 1st International Conference on Islam, Science and Technology, ICONISTECH-1 2019, 11-12 July 2019, Bandung, Indonesia},
        publisher={EAI},
        proceedings_a={ICONISTECH-1},
        year={2020},
        month={11},
        keywords={adaptive boosting glcm human face recognition k-nearest neighbor},
        doi={10.4108/eai.11-7-2019.2297826}
    }
    
  • Chairisni Lubis
    Novario Jaya Perdana
    Hengki Pranoto
    Year: 2020
    Face Recognition Application Using Adaptive Boosting and Gray Level Co-Occurrence Matrix
    ICONISTECH-1
    EAI
    DOI: 10.4108/eai.11-7-2019.2297826
Chairisni Lubis1,*, Novario Jaya Perdana1, Hengki Pranoto1
  • 1: Universitas Tarumanagara, Jakarta, Indonesia
*Contact email: chairisnil@fti.untar.ac.id

Abstract

Face recognition has been an interesting field to explore. Although some previous researches have successfully proved to detect faces, there are still some difficulties to automatically recognize whose faces in one image. Human face is a dynamic object which a high degree of variability exists in its appearance. Therefore, every face has their own uniqueness. These unique features could be used for recognizing one from the other. This research is intended to offer new approach on the field. It is done by combining three methods for both detecting and recognizing faces. It begins with applying Adaptive Boosting (AdaBoost) to detect faces on a picture, then employing Gray Level Co-Occurrence Matrix (GLCM) to extract their features. Finally, K-Nearest Neighbor is used to recognize the owner of the face. This combination of methods is proven to get significant result of face detection but only fair result of face recognition. In addition to the research, an application has been developed. After doing research and development of this application, it can be concluded that the combination of the methods could become another approach for face recognition.