Face Detection System using Linear Discriminant Analysis
Face detection is a two-class problem. Given an image, we would like to confidently say whether a face is present in it. The face detection procedure involves preprocessing of the image followed by detection. Preprocessing involves histogram equalization to improve the quality of the image. The preprocessed image is scanned to detect the edges; finally the edge-detected area is given as input to LDA classifier, which returns the location of the face, if present. The LDA classifier is trained on the whole face image. The input to the classifier would be the x and y co-ordinates of a window and the window is moved until the entire image is traced. The classifier returns an output measure, which is compared with the stored measure of image in the database, and the appropriateness is checked. The same procedure is repeated for different resolution levels and thus the face is detected.
Face detection is a computer technology that identifies human faces in arbitrary images. Face images are essential to intelligent human computer interaction, and researches in face processing include face recognition, face tracking, pose estimation, expression recognition and gesture recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required.
Face detection is one of the visual tasks, which humans can do effortlessly. However, in computer vision terms, this task is not easy. A general statement of the problem can be defined as follows: Given a still or video image, detect and localize an unknown number (if any) of faces. The solution to the problem involves segmentation, extraction, and verification of faces and possibly facial features from an uncontrolled background. As a visual front-end processor, a face detection system should also be able to achieve the task regardless of illumination, orientation, and camera distance
Given a single image or a sequence of images, the goal of face detection is to identify all the image regions, which contain a face regardless of its three-dimensional position and orientation and lighting conditions. Such a problem is challenging because faces are non-rigid and have a high degree of variability in size, shape, color, and texture and the presence of complex background. Accurate and reliable face detection is the domain of this paper.
There are three main contributions to the face detection framework. Each of these ideas is described in the subsequent sections. The first step is histogram equalization, which is done to improve the quality of the image by increasing the contrast and intensity distribution of the pixels. The second step is edge detection. Edge detection process traces the entire image and gives out the outline of the objects present in the image. The final step involves classification of the objects in the image into face or nonface. If a face is detected to be present the location of the same is given as output.
Figure 1.Architectural diagram of the system
3. Histogram equalization
The histogram in the context of image processing is the operation by which the occurrences of each intensity value in the image are shown. Normally, the histogram is a graph showing the number of pixels in an image at each different intensity value found in that image. For an 8-bit grayscale image there are 256 different possible intensities, and so the histogram will graphically display 256 numbers showing the distribution of pixels amongst those grayscale values. Histogram equalization is the technique by which the dynamic range of the histogram of an image is increased. Histogram equalization assigns the intensity values of pixels...
Please join StudyMode to read the full document