Implementation and quality measures of graph theory model based image segmentation process in medical application

Image segmentation is the foundation of further object-oriented image analysis, understanding and recognition. It is one of the key technologies in high resolution remote sensing applications. In this paper, a new fast image segmentation algorithm for high resolution remote sensing imagery is proposed, which is based on graph theory and fractal net evolution approach (FNEA). Firstly, an image is modelled as a weighted undirected graph, where nodes correspond to pixels, and edges connect adjacent pixels. An initial object layer can be obtained efficiently from graph-based segmentation, which runs in time nearly linear in the number of image pixels. Then FNEA starts with the initial object layer and a pairwise merge of its neighbour object with the aim to minimize the resulting summed heterogeneity. Furthermore, according to the character of different features in high resolution remote sensing image, three different merging criterions for image objects based on spectral and spatial information are adopted. Finally, compared with the commercial remote sensing software eCognition, the experimental results demonstrate that the efficiency of the algorithm has significantly improved, and the result can maintain good feature boundaries.

Download Full-text

p-box: a new graph model

Discrete Mathematics & Theoretical Computer Science ◽

10.46298/dmtcs.2121 ◽

2015 ◽

Vol Vol. 17 no. 1 (Graph Theory) ◽

Author(s):

Mauricio Soto ◽

Christopher Thraves-Caro

Keyword(s):

Graph Theory ◽

Graph Model ◽

Directed Path ◽

Outerplanar Graphs ◽

New Model ◽

Model Based ◽

Representative Element ◽

International Audience ◽

Graph Families

Graph Theory International audience In this document, we study the scope of the following graph model: each vertex is assigned to a box in ℝd and to a representative element that belongs to that box. Two vertices are connected by an edge if and only if its respective boxes contain the opposite representative element. We focus our study on the case where boxes (and therefore representative elements) associated to vertices are spread in ℝ. We give both, a combinatorial and an intersection characterization of the model. Based on these characterizations, we determine graph families that contain the model (e. g., boxicity 2 graphs) and others that the new model contains (e. g., rooted directed path). We also study the particular case where each representative element is the center of its respective box. In this particular case, we provide constructive representations for interval, block and outerplanar graphs. Finally, we show that the general and the particular model are not equivalent by constructing a graph family that separates the two cases.

Download Full-text

Apple Image Segmentation Model Based on R Component with Swarm Intelligence Optimization Algorithm

10.23940/ijpe.18.06.p6.11491160 ◽

2018 ◽

Author(s):

Liqun Liu

Keyword(s):

Image Segmentation ◽

Swarm Intelligence ◽

Optimization Algorithm ◽

Model Based ◽

Swarm Intelligence Optimization

Download Full-text

A REGION-BASED MULTI-SCALE APPROACH FOR OBJECT-BASED IMAGE ANALYSIS

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprsarchives-xli-b7-241-2016 ◽

2016 ◽

Vol XLI-B7 ◽

pp. 241-247 ◽

Cited By ~ 6

Author(s):

T. Kavzoglu ◽

M. Yildiz Erdemir ◽

H. Tonbul

Keyword(s):

Image Analysis ◽

Image Segmentation ◽

Classification Accuracy ◽

Scale Parameter ◽

Rate Of Change ◽

Multi Scale ◽

Object Based Image Analysis ◽

Optimal Scale ◽

Segmentation Process ◽

Object Based

Within the last two decades, object-based image analysis (OBIA) considering objects (i.e. groups of pixels) instead of pixels has gained popularity and attracted increasing interest. The most important stage of the OBIA is image segmentation that groups spectrally similar adjacent pixels considering not only the spectral features but also spatial and textural features. Although there are several parameters (scale, shape, compactness and band weights) to be set by the analyst, scale parameter stands out the most important parameter in segmentation process. Estimating optimal scale parameter is crucially important to increase the classification accuracy that depends on image resolution, image object size and characteristics of the study area. In this study, two scale-selection strategies were implemented in the image segmentation process using pan-sharped Qickbird-2 image. The first strategy estimates optimal scale parameters for the eight sub-regions. For this purpose, the local variance/rate of change (LV-RoC) graphs produced by the ESP-2 tool were analysed to determine fine, moderate and coarse scales for each region. In the second strategy, the image was segmented using the three candidate scale values (fine, moderate, coarse) determined from the LV-RoC graph calculated for whole image. The nearest neighbour classifier was applied in all segmentation experiments and equal number of pixels was randomly selected to calculate accuracy metrics (overall accuracy and kappa coefficient). Comparison of region-based and image-based segmentation was carried out on the classified images and found that region-based multi-scale OBIA produced significantly more accurate results than image-based single-scale OBIA. The difference in classification accuracy reached to 10% in terms of overall accuracy.

Download Full-text