This paper considers the problem of factorizing a matrix with missing components into a product of two smaller matrices, also known as principal component analysis with missing data (PCAMD). The Wiberg algorithm is a numerical algorithm developed for the problem in the community of applied mathematics. We argue that the algorithm has not been correctly understood in the computer vision community. Although there are many studies in our community, almost every one of which refers to the Wiberg study, as far as we know, there is no literature in which the performance of the Wiberg algorithm is investigated or the detail of the algorithm is presented. In this paper, we present derivation of the algorithm along with a problem in its implementation that needs to be carefully considered, and then examine its performance. The experimental results demonstrate that the Wiberg algorithm shows a considerably good performance, which should contradict the conventional view in our community, namely that minimization-based algorithms tend to fail to converge to a global minimum relatively frequently. The performance of the Wiberg algorithm is such that even starting with random initial values, it converges in most cases to a correct solution, even when the matrix has many missing components and the data are contaminated with very strong noise. Our conclusion is that the Wiberg algorithm can also be used as a standard algorithm for the problems of computer vision.
A general scheme t o represent the relation between dyn a m i c images and camera m o t i o n i s presented. T h e n , its application t o visual servoing i s proposed. For a specific object, the possible combination of the camera pose and the obtained image should be constrained o n a lower dimensional hyper surface within the product space of whole combination of image data and camera position. T h e visual servoing, f o r example, is interpreted as t o find a path o n this surface leading t o a gzven goal zmage. O u r approach zs t o analyze the properties of this surface, and utilize its diferential or tangential property f o r visual servoing. For this approach, the dimension of the image informatzon becomes key problem. We propose t o use the principal component analysis and t o represent images with a composition of small n u m b e r of "eigenimages " b y uszng K-L (Karhunen-Lohe) expansion. I n this paper, we describe, first, that a normal vect o r of this surface i s related t o the so-called Interaction Matrix, and confirm the feasibility of our basic idea f o r vzsual servozng with a prelzminary experiment. T h e n , we present a dynamical estimatzon of the normal vectors t o move robot a r m mounting a camera t o a goal position where a given goal image will be obtained. We also consider the construction of the eigen space (the eigenimage space) t o represent images eficiently and t o speedu p convergence in the control. Experimental results of visual servoing with proposed method show the feasibility and applicability of o u r newly proposed approach.
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.