Fusion of Face Recognition Method - Research Paper Example

FUSION OF FACE RECOGNITION METHOD - EIGENFACES (BIOMETRICS) METHODOLOGY Eigenface face recognition system comprises chiefly of two parts. Firstly eigenface basis are created (procedure of constructing eigenfaces). Then, once the eigenfaces are constructed, face recognition or detection of a new face follows. Figure 1 outlines the general flow of the eigenface face recognition system. "Learning" a face Transform it to face space Record the resulting vector (which will be much smaller than the image). Recognizing a known face Transform the image presented for recognition to face space. Take inner products with each of the learned face space vectors. If one of these inner products is above the threshold, take the largest one and return that its owner also owns the new face. Otherwise, it's an unknown face. Optionally add it to the collection of known faces as "Unknown Person #1". (Danner, T. & Datta, Indraneel, "Eigenfaces Group - Algorithmics", par. 5-6). Source: (Krueger, J, et al, "Obtaining the Eigenface Basis"). Figure 1 General Flow of Eigenface Face Recognition System Evaluating "face-ness" of an image If unsure whether an image is a face or not, transform it to face space, then do the inverse transform to get a new image back (Danner, T. & Datta, Indraneel, "Eigenfaces Group - Algorithmics", par. 7). ANALYSIS To illustrate the methodology mentioned, consider the eigenface in Figure 2. It presents the possible face images that can be matched perfectly or closely enough. Figure 2 Eigenface and its possible Image Match After scrutinizing the images, we can observe some similar features of the eigenface from the three original images (Amber1, Andy2, and Jimmy3). Figure 3 details these matches considering Amber1 and Andy2 (dashed arrows points to some of the analogous features that may be distinguished from the eigenface). Figure 3 Comparing Amber1 and Andy2 Figure 3 shows the matches considering Amber1 and Jimmy3 (dashed arrows points to some of the analogous features that may be distinguished from the eigenface). Figure 4 Comparing Amber1 and Jimmy3 It was observed (from Figure 1 and 2) that Amber1 have more distinguished features from the eigenface. Thus we can say that the eigenface closely and strongly resembles Amber1. Amber1's reconstructed images (shown in Figure 5 - include the step by step reconstruction of Amber1's face contained in folder "ReconstructedPictures") supports this observation. DISCUSSION In order for us to be able to "learn" a face, determining what these eigenfaces are is the root of this technique. Before finding the eigenfaces, however, 'we first need to collect a set of face images. These face images become our database of known faces. We will later determine whether or not an unknown face matches any of these known faces. All face images must be the same size (in pixels), and for our purposes, they must be grayscale (shown in Figure 6), with values ranging from 0 to 255' (Krueger, J, et al, "Obtaining the Eigenface Basis"). Figure 6 Grayscale Pictures of Face Images Eigenfaces are basically basis vectors for real faces. This can be related straightforwardly to one of the most basic concepts in electrical engineering: Fourier analysis. Fourier analysis discloses that "a sum of weighted sinusoids at differing frequencies can recompose a signal perfectly"! In the same manner a "sum of weighted eigenfaces can seamlessly reconstruct a specific person's face". (Krueger, J, et al, "Obtaining the Eigenface Basis") CONCLUSION According to Krueger, J. & et al, "the eigenface technique is a powerful yet simple solution to the face recognition dilemma. In fact, it is really the most intuitive way to classify a face. As we have shown, old techniques focused on particular features of the face. The eigenface technique uses much more information by classifying faces based on general facial patterns. These patterns include, but are not limited to, the specific features of the face. By using more information, eigenface analysis is naturally more effective than feature-based face recognition." ("Obtaining the Eigenface Basis") REFERENCES Krueger, J, et al. Obtaining the Eigenface Basis. 17 Dec. 2004. Connexions. 13 Dec. 2008 . Danner, T. & Datta, Indraneel. Eigenfaces Group - Algorithmics. 17 Dec. 1999. Eigenfaces Group. 12 Dec. 2008. Read More