Abstract. Principal Component Analysis (PCA) is a powerful and widely used tool in Computer Vision and is applied, e.g., for dimensionality reduction. But as a drawback, it is not robust to outliers. Hence, if the input data is corrupted, an arbitrarily wrong representation is obtained. To overcome this problem, various methods have been proposed to robustly estimate the PCA coefficients, but these methods are computationally too expensive for practical applications. Thus, in this paper we propose a novel fast and robust PCA (FR-PCA), which drastically reduces the computational effort. Moreover, more accurate representations are obtained. In particular, we propose a two-stage outlier detection procedure, where in the first stage outliers are detected by analyzing a large number of smaller subspaces. In the second stage, remaining outliers are detected by a robust least-square fitting. To show these benefits, in the experiments we evaluate the FR-PCA method for the task of robust image reconstruction on the publicly available ALOI database. The results clearly show that our approach outperforms existing methods in terms of accuracy and speed when processing corrupted data.
We present an approach for unsupervised alignment of an ensemble of images called congealing. Our algorithm is based on image registration using the mutual information measure as a cost function. The cost function is optimized by a standard gradient descent method in a multiresolution scheme. As opposed to other congealing methods, which use the SSD measure, the mutual information measure is better suited as a similarity measure for registering images since no prior assumptions on the relation of intensities between images are required. We present alignment results on the MNIST handwritten digit database and on facial images obtained from the CVL database.
Facial image analysis is an important computer vision topic as a first step for biometric applications like face recognition/verification. The ICAO specification defines criteria to assess suitability of facial images for later use in such tasks. This standard prohibits photographs showing occlusions, thus there is the need to detect occluded images automatically. In this work we present a novel algorithm for occlusion detection and evaluate its performance on several databases. First, we use the publicly available AR faces database which contains many occluded face image samples. We show a straight-forward algorithm based on color space techniques which gives a very high performance on this database. We conclude that the AR faces database is too simple to evaluate occlusions and propose our own, more complex database, which includes, e.g., hands or arbitrary objects covering the face. Finally we extend our first algorithm by an Active Shape Model in combination with a PCA reconstruction verification. We show how our novel occlusion detection algorithm outperforms the simple approach on our more complex database.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.