2017 International Artificial Intelligence and Data Processing Symposium (IDAP), Malatya, Türkiye, 16 - 17 Eylül 2017
Facial landmark is to be determined point by point of areas such as eyes, nose, mouth, eyebrows on the face. Facial recognition studies can be generally categorized into two categories, local and global. All of the faces are used in the global face recognition while the face domain is divided into subspaces in the local face recognition. In face recognition studies facial landmarks are used for facial recognition with detection of regions located at the face and image processing methods. In this study, face recognition has been successfully analyzed using distance and slope between facial landmarks. Analyzes were performed with both statistical and classifiers. According to the results obtained, the distance and slope between the 14 landmarks used in the study were found to be statistically significant in the facial recognition. In addition, the classification was performed with the help of these features and the highest success was found with 94.60% with MLP classifier. Obtained findings show the usability of the distance and slope between the landmarks in facial recognition.