Connectivity-enforcing Hough transform for the robust extraction of line segments.

Global voting schemes based on the Hough transform (HT) have been widely used to robustly detect lines in images. However, since the votes do not take line connectivity into account, these methods do not deal well with cluttered images. On the other hand, the so-called local methods enforce connectivity but lack robustness to deal with challenging situations that occur in many realistic scenarios, e.

Revisiting complex moments for 2-D shape representation and image normalization.

When comparing 2-D shapes, a key issue is their normalization. Translation and scale are easily taken care of by removing the mean and normalizing the energy. However, defining and computing the orientation of a 2-D shape is not so simple.

Simultaneous registration and intensity normalization of SPECT perfusion images.

The analysis of 3D SPECT brain images requires several pre-processing steps such as registration, intensity normalization and brain extraction. Usually, registration is performed before intensity normalization, which requires robust registration methods, such as those based on the maximization of the Mutual Information (MI), which are computationally complex. In this paper we propose using a computationally simple method to perform the simultaneous registration and intensity normalization of SPECT brain perfusion images.

Figure-ground segmentation from occlusion.

Layered video representations are increasingly popular; see [2] for a recent review. Segmentation of moving objects is a key step for automating such representations. Current motion segmentation methods either fail to segment moving objects in low-textured regions or are computationally very expensive.

Orientation in manhattan: equiprojective classes and sequential estimation.

The problem of inferring 3D orientation of a camera from video sequences has been mostly addressed by first computing correspondences of image features. This intermediate step is now seen as the main bottleneck of those approaches. In this paper, we propose a new 3D orientation estimation method for urban (indoor and outdoor) environments, which avoids correspondences between frames.