<![CDATA[Feature extraction can be done on an objects in the form of images using several features. Feature extraction can be combined with the science of biometrics. Biometrics are unique dan measurable physical or biological characteristics. Biometric identification can be used to improve security dan avoid using fake identities. In this case, uses the palm of the object of research because palm has unique features that are different for each individual. In addition to unique features, the palm surface area is one of the authors' considerations in determining the object of research. The surface area of ​​the palm is greater than the surface area of ​​one finger. One method that can be utilized in the identification process is the LBP (Local Binary Pattern) feature extraction method that applies neighboring distances dan the number of neighbors compared. It starts with the Pre-processing stage or the preparation stage of the color image which will be transformed into a gray image dan then followed by a regioning process or image sharing process into several sub-regions. Followed by feature extraction stages with the LBP method. The highest accuracy results obtained from this study amounted to 92.31% with neighboring distance 2, number of neighbors compared = 8, number of regions = 16 dan number of shares height = 4 dan width = 4.]]>
Copyrights © 2019
