Oleh : Ade Mahendra Lubis; Jeffrey Joson; Muhammad Zullidar; Alexander A. S. Gunawan
Many researchers in the field of artificial intelligence to develop a variety of methods including face recognition method. Face recognition can be performed by various methods. But with so many existing face recognition methods will cause confusion in the selection of the method will be applied. This thesis discusses the performance of Local Binary Pattern. Design method used is a rapid application development. Rapid application development flow chosen because it has a short application development, so application development can finish so quickly. And this method allows developers and researchers often interact so as to produce a good application and in accordance with the criteria of the researcher. In the test analysis performed on the speed and accuracy of face recognition process based on changes in the threshold value and the face angle positions. Local Binary Pattern is expected that this algorithm can be used for applications that have a processor with lower computing. The results obtained when used threshold of 75 and there are variations in face angle positions 0 and 45 degrees. Through the results it can be concluded Local Binary Pattern method can give good results in face recognition.
Published at : Updated