An Overview of Face Detection Methods in Angular Positions

Today, face detection is of paramount importance due to its wide range of benefits and applications. Results of studies in this field have led to obtaining methods for face detection. In each of these methods, two factors of accuracy and runtime are important. The necessity of using accurate and quick methods has led to more studies in this regard. In face images, the individual’s face is not always directed toward the camera. Therefore, one of the important challenges in face detection is the correct detection when the angle of the image to the camera is not in the same direction and there are differences in the degree measure of the image angle, compared to the main image. The main issue in face detection, which has always been considered an important concept, is achieving the desired result based on the needs of security departments and scientific organizations. The present study aimed to evaluate the face detection methods in angular positions. In addition, one of the objectives of the research was assessing the advantages and disadvantages of each technique. In the end, the evaluated methods were compared on databases of ORL, ORL, and ORL in terms of accuracy of face detection. According to the results, the PCA+LDA+GABOR was the most efficient method due to special attention to viewing angles in different images that can result in high detection accuracy, compared to other methods.