Edge Detection Model Performance Using Canny, Prewitt and Sobel in Face Detection

Abstract

Detection of objects in the form of objects, humans and other objects at this time has been widely applied in many aspects of life. The help of this technology can facilitate human work, one of which is facial detection to get information about a person's identity. Face identification and detection is closely related to Data Mining science with Image Processing sub-science. This facial detection and recognition can use several technical approaches, one of which is to use edge detection. Edge detection is one of the basic operations of image processing. In the image classification process, edge detection is required before image segmentation processing. There are several methods that can be used to perform edge detection such as Canny, Prewitt and Sobel. These three methods are methods that have accurate and good detection results, with the advantages of each method having its own added value. From the results of previous studies that stated these three methods have good results, it became interesting to conduct a comparative study of these three methods in detecting edges in facial images. Edge detection applied to this study identifies facial images, and will get similarities with the original image from the result analysis process, and is reinforced by measurement results using the Mean Square Error error degree. The final result of this study states that this study the most optimal Mean Square Error measurement results obtained the final results in the Canny method of 10, the Prewitt method of 41 and Sobel of 29. These results show that the value of the Canny method has the smallest Mean Square Error value, which indicates that the Canny method on facial image edge detection has the most optimal results.