附录(原文及译文)
翻译原文来自
Thomas David Heltine BSc. Hons.pig什么意思 The University of York
Department of Computer Science
料理鼠王英文版For the Qualification of PhD. -- September 2005 -
plumblossom
《Face Recognition: Two-Dimensional and Three-Dimensional Techniques》
4 Two-dimensional Face Recognition
4.1 Feature Localization
Before discussing the methods of comparing two facial images we now take a brief look at some at the preliminary process of facial feature alignment. This process typically consists of two stages: face detection and eye localisation. Depending on the application, if
the position of the face within the image is known beforehand (for a cooperative subject in a door access system for example) then the face detection stage can often be skipped, as the region of interest is already known. Therefore, we discuss eye localisation here, with a brief discussion of face detection in the literature review(ction 3.1.1).
The eye localisation method is ud to align the 2D face images of the various test ts ud throughout this ction. However, to ensure that all results prented are
reprentative of the face recognition accuracy and not a product of the performance of the eye localisation routine, all image alignments are manually checked and any errors corrected, prior to testing and evaluation.
We detect the position of the eyes within an image using a simple template badthursday的音标
method. A training t of manually pre-aligned images of faces is taken, and each
image cropped to an area around both eyes. The average image is calculated and ud
as a template.
idler
Figure 4-1 - The average eyes. Ud as a template for eye detection.
Both eyes are included in a single template, rather than individually arching for each eye in turn, as the characteristic symmetry of the eyes either side of the no, provides a uful feature that helps distinguish between the eyes and other fal positives that may be picked up in the background. Although this method is highly susceptible to subject distance from the camera) and also introduces the assumption that eyes in the image appear near horizontal. Some preliminary experimentation also reveals that it is advantageous to include the area of skin just beneath the eyes. The reason being that in some cas the eyebrows can cloly match the template, particularly if there are shadows in the eye-sockets, but the area of skin below the eyes helps to distinguish the eyes from eyebrows (the area just below the eyebrows contain eyes, whereas the area below the eyes contains only plain skin).
A window is pasd over the test images and the absolute difference taken to that of the average eye image shown above. The area of the image with the lowest difference is taken as the region of interest containing the eyes. Applying the same procedure using a smaller template of the individual left and right eyes then refines each eye position.
This basic template-bad method of eye localisation, although providing fairly precilocalisations, often fails to locate the eyes completely. However, we are able to
improve performance by including a weighting scheme.
Eye localisation is performed on the t of training images, which is then parated into two ts: tho in which eye detection was successful; and tho in which eye detection failed. Taking the t of successful localisations we compute the average distance from the eye template (Figure 4-2 top). Note that the image is quite dark, indicating that the detected eyes correlate cloly to the eye template, as we would expect. However, bright points do occur near the whites of the eye, suggesting that this area is often inconsistent, varying greatly from the average eye template.
Figure 4-2 – Distance to the eye template for successful detections (top) indicating variance due to
皇后大学noi and failed detections (bottom) showing credible variance due to miss-detected features.
In the lower image (Figure 4-2 bottom), we have taken the t of failed localisations(images of the forehead, no, cheeks, background etc. fally detected by the localisation routine) and once again computed the average distance from the eye template. The bright pupils surrounded by darker areas indicate that a failed match is often due to the high correlation of the no and cheekbone regions overwhelming the poorly correlated pupils. Wanting to emphasi the difference of the pupil regions for thes
hexe failed matches and minimi the variance of the whites of the eyes for successful matches, we divide the lower image values by the upper image to produce a weights vector as shown in Figure 4-3. When applied to the difference image before summing a total error, this weighting scheme provides a much improved detection rate.
南京师范大学继续教育学院Figure 4-3 - Eye template weights ud to give higher priority to tho pixels that best reprent the eyes.
4.2 The Direct Correlation Approach
We begin our investigation into face recognition with perhaps the simplest approach,known as the direct correlation method (also referred to as template matching by Brunelli and Poggio [ 29 ]) involving the direct comparison of pixel intensity values taken from facial images. We u the term ‘Direct Correlation’ to encompass all techniques in which face images are compared directly, without any form of image space
英文自我简介
analysis, weighting schemes or feature extraction, regardless of the distance metric ud. Therefore, we do not infer that Pearson’s correlation is applied as the similarity function (although such an approach would obviously come under our definition of direct correlation). We typically u the Euclidean distance as our metric in the investigations (inverly related to Pearson’s correlation and can be considered as a scale and translation nsitive form of image correlation), as this persists with the contrast made between image space and subspace approaches in later ctions.
