Improving and Filtering Localization

The localization procedure thus yields an output similar to the one found in Figure . Note that the horizontal (i.e., parallel with intra-ocular axis) position of the nose is uncertain. This is represented by a white line across the vertical position of the nose from the left eye to the right eye. The nose tip is a point on this line segment and its exact locus is found by the techniques described in Chapter 4. Furthermore, it is possible that the face detection computation will be triggered by a non-face which happens to have a blob-like structure with eye blobs and a mouth-limb. These 'false alarms' by the face detector will be rejected using techniques described in Chapter 4.

  

Figure 3.32: A typical output of the face detection stage.

Thus, we have given a procedure for localizing the face and facial features in an image. We begin by finding the face-blob and then estimating a facial contour. From there, we can define the eye-band, a region where the eyes might be present. Eye-blob detection is then performed and the blobs are tested geometrically to see if an adequate pair can be found. If two blobs are ``eye-like'' geometrically, we search for a mouth between them and then, finally, a nose-line. At this stage, however, the localization is not complete and requires further development in Chapter 4. Consequently, we shall defer localization testing to Chapter 5. Several examples of the complete localization are given there. It is also important to note that the exact location of the facial features in Figure  (and other faces that are processed) is not critical. This is because this localization is to undergo further processing before face recognition is performed. This post-processing will desensitize the recognition to small localization errors.