Statistical 3D Segmentation With Greedy Connected Component Labelling Refinement
نویسندگان
چکیده
A new approach for segmenting 3D voxel data sets is presented. It is semi-automatic and consists of two phases. First, the initial segmentation is accomplished by voxel labeling using statistical maximum likelihood estimation techniques. The novelty of the present approach is that the type probability distribution function is not required a priori. A multi-parameter distribution which includes a variety of widely applicable distributions is utilized. The second phase refines the segmentation by the use of a new greedy connected component labeling (GCCL). The overall effectiveness of this new approach is illustrated with data examples of multichannel laser scanning confocal microscope (LSCM) images where the structure of GFAP (a protein) and nuclei, and the geometry of an electrode implant are extracted. CR Categories: I.4.6 [Image Processing and Computer Version ]: segmentation—Region growing, partitioning; I.4.10 [Image Processing and Computer Version]: Image Representation— Statistical, Volumetric
منابع مشابه
Bayesian Image Segmentation through Level Lines Selection
Bayesian statistical theory is a convenient way of taking a priori information into consideration when inference is made from images. In Bayesian image segmentation, the a priori distribution should capture the knowledge about objects. Taking inspiration from (Alvarez et al., 1999), we design a prior density that penalizes the area of homogeneous parts in images. The segmentation problem is fur...
متن کاملOn the Minimum Labelling Spanning bi-Connected Subgraph problem
We introduce the minimum labelling spanning bi-connected subgraph problem (MLSBP) replacing connectivity by bi-connectivity in the well known minimum labelling spanning tree problem (MLSTP). A graph is bi-connected if, for every two vertices, there are, at least, two vertex-disjoint paths joining them. The problem consists in finding the spanning bi-connected subgraph or block with minimum set ...
متن کاملSelf-learning Segmentation and Classification of Cell-Nuclei in 3D Volumetric Data Using Voxel-Wise Gray Scale Invariants
We introduce and discuss a new method for segmentation and classification of cells from 3D tissue probes. The anisotropic 3D volumetric data of fluorescent marked cell nuclei is recorded by a confocal laser scanning microscope (LSM). Voxel-wise gray scale features (see accompaning paper [1][2]), invariant towards 3D rotation of its neighborhood, are extracted from the original data by integrati...
متن کاملEfficient Modularity Optimization: Multi-Step Greedy Algorithm and Vertex Mover Refinement
Identifying strongly connected substructures in large networks provides insight into their coarse-grained organization. Several approaches based on the optimization of a quality function, e.g., the modularity, have been proposed. We present here a multistep extension of the greedy algorithm (MSG) that allows the merging of more than one pair of communities at each iteration step. The essential ...
متن کاملAccelerated hardware object extraction and labelling: from object segmentation to connected components labelling
This paper demonstrates the use of a single-chip FPGA for the segmentation of moving objects in a video sequence. The system maintains highly accurate background models, and integrates the detection of foreground pixels with the conversion into labelled objects using a connected component labelling algorithm. The background models are based on 24-bit RGB values and 8-bit greyscale intensity val...
متن کامل