Computational and Performance Aspects of PCA-Based Face-Recognition Algorithms

Abstract

Algorithms based on principal component analysis (PCA) form the basis of numerous studies in the psychological and algorithmic face-recognition literature. PCA is a statistical technique and its incorporation into a face-recognition algorithm requires numerous design decisions. We explicitly state the design decisions by introducing a generic modular PCA-algorithm. This allows us to investigate these decisions, including those not documented in the literature. We experimented with different implementations of each module, and evaluated the different implementations using the September 1996 FERET evaluation protocol (the de facto standard for evaluating face-recognition algorithms). We experimented with (i) changing the illumination normalization procedure; (ii) studying effects on algorithm performance of compressing images with JPEG and wavelet compression algorithms; (iii) varying the number of eigenvectors in the representation; and (iv) changing the similarity measure in the classification process. We performed two experiments. In the first experiment, we obtained performance results on the standard September 1996 FERET large-gallery image sets. In the second experiment, we examined the variability in algorithm performance on different sets of facial images. The study was performed on 100 randomly generated image sets (galleries) of the same size. Our two most significant results are (i) changing the similarity measure produced the greatest change in performance, and (ii) that difference in performance of +/- 10% is needed to distinguish between algorithms.

A Probability Model for Combining Ranks

“…Of the 10 algorithms we selected three dominant algorithms. From the baseline algorithms we choose to use the ANM algorithm which uses a Mahalanobis distance variation on angular distances for eigenfaces [ 7]. Within the class of baseline algorithms this algorithm was strong.…”

Bilgisayar Kullanıcılarına Yönelik Duygusal İfade Tespiti

“…Parmak izi tanıma [3], göz hareketi ve iris tanıma [4], el-yazısı tanıma [5], tuş vuruşu tanıma [6], hareket tanıma [7], el işareti tanıma [8], yüz tanıma [9] gibi sistemler bunlara örnek olarak verilebilir. Yüz tanıma, bireye dışarıdan herhangi bir müdahale olmadan kişisel kimliğini doğrulama ve modellemeye imkân sağlayan bir yöntemdir [10].…”

Tell Me What You Like and I’ll Tell You What You Are: Discriminating Visual Preferences on Flickr Data

“…To show the results, we build a CMC curve [25], a common performance measure in the field of re-identification [26]: given a test set of images coming from a single user and the membership score discussed, the curve tells the rate at which the correct user is found within the first k matches, with all possible k spanned on the x-axis. Figure 2 shows various CMC curves for our dataset.…”