Abstract An automated region growing algorithm has been adapted for multi-class segmentation. The algorithm does not need initial parameters. It automatically finds a start region which is required by each of the region growing processes performed during multi-class segmentation. A new method for finding start region is proposed. The multi-class region growing algorithm was tested on CT and MRI...

We present an incremental approach to motion segmentation. Feature points are detected and tracked throughout an image sequence, and the features are grouped using a region-growing algorithm with an affine motion model. The primary parameter used by the algorithm is the amount of evidence that must accumulate before features are grouped. Contrasted with previous work, the algorithm allows for a...

The downhill filter is an elegant and efficient single pass reconstruction algorithm which demonstrates fast and consistent performance. It operates through a controlled process of region growing by ordered aggregation of surface pixels onto an expanding shell. 2004 Elsevier B.V. All rights reserved.

We present a simple and efficient dense matching method based on region growing techniques, which can be applied to a wide range of globally textured images like many outdoor scenes. Our method can deal with non-rigid scenes and large camera motions. First a few highly distinctive features like points or areas are extracted and matched. These initial matches are then used in a correlation-based...

We propose an automatic procedure for the correct segmentation of grey and white matter in MR data sets of the human brain. Our method exploits general anatomical knowledge for the initial segmentation and for the subsequent refinement of the estimation of the cortical grey matter. Our results are comparable to manual segmentations.

A spread pattern of a tumor in medical images is an important factor for classification of the tumor. The spread pattern is generally not considered when we use only one segment for classification. In order to include the spread pattern for tumor analysis, we propose an approach for classification of tumors in mammograms using two segments for a mass. The proposed approach is performed in two s...

The cardiac conduction system (CCS) has been in the spot light of the clinical and modeling community in recent years because of its fundament role in physiology and pathophysiology of the heart. Experimental research has focused mainly on investigating the electrical properties of the Purkinje-ventricular-junctions (PVJs). The structure of the PVJs has only been described through schematic dra...

Bottom-up segmentation methods merge similar neighboring regions according to a decision rule and a merging order. In this paper, we propose a contribution for each of these two points. Firstly, under statistical hypothesis of similarity, we provide an improved decision rule for region merging based on significance tests and the recent statistical inequality of McDiarmid. Secondly, we propose a...

In this paper, we present a task-specific segmentation method that incorporates semantic knowledge into datadriven segmentation process through different region merge scores. Starting from a simple region growing algorithm which results in over-segmented regions, we apply region merging method designed specifically for each task such as road extraction or vegetation area identification. Further...

We describe an Eikonal-based algorithm for computing dense oversegmentation of an image, often called superpixels. This oversegmentation respect local image boundaries while limiting undersegmentation. The proposed algorithm relies on a region growing scheme, where the potential map used is not xed and evolves during the di usion. Re nement steps are also proposed to enhance at low cost the rst...