The use of interest point detectors and SIFT descriptors for face recognition is studied in this paper. There are two main novelties with respect to previous approaches using SIFT features. First, the use of two scale-invariant interest point detectors (namely, Harris-Laplace and difference of Gaussians) which are combined in order to detect both corner-like structures and blob-like structures in face images. Second, the distance measure used, which takes into account both the number of matching points found between two images (according to their SIFT descriptors) and the coherence of these matches in terms of scales, orientations and spacial configuration. The results obtained with our model-based algorithm are compared with those of a classic appearance-based face recognition method (PCA) over two different face databases: the well-known AT&T database and a face database created at our university.

Recently, a number of empirical studies have compared the performance of PCA and ICA as feature extraction methods in appearance-based object recognition systems, with mixed and seemingly contradictory results. In this paper, we briefly describe the connection between the two methods and argue that whitened PCA may yield identical results to ICA in some cases. Furthermore, we describe the specific situations in which ICA might significantly improve on PCA.

A redundancy resolution technique devoted to grasp synthesis is presented. Given a set of contact points and a certain robot arm and gripper, the goal is to select both the best assignment of gripper fingers to contact points and the best joint values that allow the fingers to reach such contact points. The system proposed is based on the generation of an inverse kinematics tree where fast searches can be performed in order to find the optimum configuration. Optimality is defined as similarity to previously stored examples over a hierarchical structure of configuration data, which includes finger assignments and robot joints.

This paper presents a visual tracking system developed for a teleoperation project. The goal of this project is a both hands master-slave system in which the operator needs to see the robot hand (gripper) every time. For this reason, a new and robust algorithm to track the robot hand during its movement is developed. This is a model based tracking so the knowledge of the robot hand CAD model is needed (pose is obtained). This information is used to move a pan-tilt camera and keep the gripper centered in the image using an adaptive fuzzy logic controller. Due to the continuous gripper movement, we need a position predictor to reduce the error. In our case, the extended Kalman filter - EKF is used to do it. Vision based systems have a lot of empirically adjustable parameters for a good working. With the algorithm proposed in this paper, some parameters are auto-adjustable, so the system is easier to use and the robustness is increased.

This work presents a method for identifying real three-dimensional objects in non-controlled backgrounds using independent component analysis to eliminate redundant image information present in each object image. The proposed method is a two-step process that allows a coarse color-based detection and an exact localization using shape information. The paper describes an efficient implementation, making this approach suitable for real-time applications.