It is known that neurons in area V2 (the second visual area) can signal the orientation of illusory contours in the primate. Whether area V1 (primary visual cortex) can signal illusory contour orientation is more controversial. While some electrophysiology studies have ruled out illusory signaling in V1, other reports suggest that V1 shows some illusory-specific response. Here, using optical im...

We propose a new method for contour tracking in video. The inverted distance transform of the edge map is used as an edge indicator function for contour detection. Using the concept of topographical distance, the watershed segmentation can be formulated as a minimization. This new viewpoint gives a way to combine the results of the watershed algorithm on different surfaces. In particular, our a...

This paper presents an active contour tracking algorithm based on the particle filter for a non-rigid object in cluttered scenes. We decompose the non-rigid contour tracking problem into three parts as transition estimation, deformation detection, and shape regulation. We use an affine transform dynamic model and employ the particle filter to estimate the parameters. We generate a probabilistic...

In this paper, we present ConGrap, a novel contour detector that uses the Gradient Map and results in closed contours with semantic connections. In contrast to common edge and contour detections, ConGrap not only produces an edge image, but also provides additional information (e.g. the borderline pixel coordinates, the bounding box, etc.) about every contour. Additionally, the resulting contou...

The spatial relationships of contours play important roles in many areas such as extracting topographic features from contour maps, automatically identifying elevations of scanned contours, et al.. In those areas, one key issue is making computers identify the relationships of contours. The spatial relationships of contours are usually represented by contour tree. Contour tree is essentially a ...

Many physical phenomena have complex structure in both space and time. To systematically understand these phenomena from images we need representations that unify the treatment of space and time. We create such a representation, the space-time map, for characterizing contour evolutions. Many types of information are computed and stored as facets of the map, registered to a space-time manifold g...

This paper presents a non-parametric MAP framework for tracking non-rigid video objects. We formulate the region tracking problem as a maximum a posteriori probability (MAP) problem and define the probabilistic models in terms of the distances between the intensity distribution of the object and that of its spatialand temporal-neighborhood. Furthermore, in order to better model the complex inte...

A key challenge in molecular systems biology is understanding how new pathways arise during evolution and how to exploit them for biotechnological applications. New pathways in metabolic networks often evolve by recruiting weak promiscuous activities of pre-existing enzymes. Here we describe recent systems biology advances to map such 'underground' activities and to predict and analyze their co...