Comparative analysis of modern automated algorithms image segmentation

2012 ◽  
Vol 16 (5) ◽  
pp. 37-47
Author(s):  
O.M. Lisenko ◽  
A.YU. Varfolomєєv
Keyword(s):  
Image Segmentation ◽  
Comparative Analysis ◽  
Expectation Maximization ◽  
Mean Shift ◽  
Natural Images ◽  
Region Merging ◽  
Segmentation Algorithms ◽  
Automated Algorithms ◽  
Unsupervised Image Segmentation ◽  
Statistical Region Merging

Unsupervised image segmentation algorithms based on-mean clustering, expectation-maximization, mean-shift, normalized graph cut, weighted aggregation, statistical region merging, JSEG, HGS and ROI-SEG are considered. The results of segmentation obtained by mentioned algorithms on textural, satellite and natural images are presented. The analysis of quality and segmentation speed of each algorithm realization is performed

FAST INTERACTIVE REGIONAL PATTERN MERGING FOR GENERIC TISSUE SEGMENTATION IN HISTOPATHOLOGY IMAGES

2021 ◽  
pp. 2150012
Author(s):  
Kuo-Lung Lor ◽  
Chung-Ming Chen
Keyword(s):  
Image Segmentation ◽  
Color Image ◽  
Linear Time ◽  
Mean Shift ◽  
Texture Features ◽  
Color Image Segmentation ◽  
Image Size ◽  
Region Merging ◽  
Tissue Segmentation ◽  
Regional Pattern

The image segmentation of histopathological tissue images has always been a challenge due to the overlapping of tissue color distributions, the complexity of extracellular texture and the large image size. In this paper, we introduce a new region-merging algorithm, namely, the Regional Pattern Merging (RPM) for interactive color image segmentation and annotation, by efficiently retrieving and applying the user’s prior knowledge of stroke-based interaction. Low-level color/texture features of each region are used to compose a regional pattern adapted to differentiating a foreground object from the background scene. This iterative region-merging is based on a modified Region Adjacency Graph (RAG) model built from initial segmented results of the mean shift to speed up the merging process. The foreground region of interest (ROI) is segmented by the reduction of the background region and discrimination of uncertain regions. We then compare our method against state-of-the-art interactive image segmentation algorithms in both natural images and histological images. Taking into account the homogeneity of both color and texture, the resulting semi-supervised classification and interactive segmentation capture histological structures more completely than other intensity or color-based methods. Experimental results show that the merging of the RAG model runs in a linear time according to the number of graph edges, which is essentially faster than both traditional graph-based and region-based methods.

Research of Remote Sensing Image Segmentation Based on Mean Shift and Region Merging

2011 ◽  
Vol 90-93 ◽  
pp. 2836-2839 ◽  
Author(s):  
Jian Cui ◽  
Dong Ling Ma ◽  
Ming Yang Yu ◽  
Ying Zhou
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
Large Scale ◽  
Mean Shift ◽  
Image Features ◽  
Small Scale ◽  
Region Merging ◽  
Segmentation Method ◽  
Shift Method ◽  
Scale Parameters

In order to extract ground information more accurately, it is important to find an image segmentation method to make the segmented features match the ground objects. We proposed an image segmentation method based on mean shift and region merging. With this method, we first segmented the image by using mean shift method and small-scale parameters. According to the region merging homogeneity rule, image features were merged and large-scale image layers were generated. What’s more, Multi-level image object layers were created through scaling method. The test of segmenting remote sensing images showed that the method was effective and feasible, which laid a foundation for object-oriented information extraction.

Region Merging Based Segmentation with Cellular Automaton

2013 ◽  
Vol 394 ◽  
pp. 410-415
Author(s):  
Yong Hui Gao ◽  
Sheng Zheng Wang ◽  
Jie Yang
Keyword(s):  
Image Segmentation ◽  
Cellular Automaton ◽  
Good Alternative ◽  
Natural Images ◽  
Region Merging ◽  
Rule Based ◽  
Interactive Method ◽  
Whole Process ◽  
Similarity Threshold ◽  
Fully Automatic

Since fully automatic image segmentation on natural images is usually hard to provide guaranteed results, interactive scheme with a few simple user inputs becomes a good alternative. This paper presents a novel interactive method based on regional attacking and merging mechanism within a cellular automaton (CA) framework. With an attacking rule based on regions maximal similarity, the adjacent homogeneous regions that are initialized by pre-segmentation are automatically merged and labeled, the users only need to indicate the object and background regions with rough markers. The whole process neednt set any similarity threshold in advance and the desired contours are effectively extracted by labeling all the non-marker regions as either background or object. Extensive experiments are performed and the results show that the proposed scheme can reliably extract the object contours from the complex background.

scholarly journals MULTISCALE SEGMENTATION OF POLARIMETRIC SAR IMAGE BASED ON SRM SUPERPIXELS

2016 ◽  
Vol XLI-B7 ◽  
pp. 283-287
Author(s):  
F. Lang ◽  
J. Yang ◽  
L. Wu ◽  
D. Li
Keyword(s):  
Object Oriented ◽  
Test Site ◽  
Region Merging ◽  
Polarimetric Sar ◽  
Multi Scale ◽  
Single Scale ◽  
Binary Partition ◽  
Segmentation Algorithms ◽  
Merging Process ◽  
Statistical Region Merging

Multi-scale segmentation of remote sensing image is more systematic and more convenient for the object-oriented image analysis compared to single-scale segmentation. However, the existing pixel-based polarimetric SAR (PolSAR) image multi-scale segmentation algorithms are usually inefficient and impractical. In this paper, we proposed a superpixel-based binary partition tree (BPT) segmentation algorithm by combining the generalized statistical region merging (GSRM) algorithm and the BPT algorithm. First, superpixels are obtained by setting a maximum region number threshold to GSRM. Then, the region merging process of the BPT algorithm is implemented based on superpixels but not pixels. The proposed algorithm inherits the advantages of both GSRM and BPT. The operation efficiency is obviously improved compared to the pixel-based BPT segmentation. Experiments using the Lband ESAR image over the Oberpfaffenhofen test site proved the effectiveness of the proposed method.

scholarly journals Adaptive Hybrid Blood Cell Image Segmentation

2019 ◽  
Vol 255 ◽  
pp. 01001
Author(s):  
T. Muda T Zalizam ◽  
Abdul Salam Rosalina ◽  
Ismail Suzilah
Keyword(s):  
Image Segmentation ◽  
Blood Cell ◽  
Mean Shift ◽  
Recognition System ◽  
Medical Diagnostics ◽  
Cell Analysis ◽  
Hybrid Analysis ◽  
Crucial Step ◽  
Cell Image ◽  
Segmentation Algorithms

Image segmentation is an important phase in the image recognition system. In medical imaging such as blood cell analysis, it becomes a crucial step in quantitative cytophotometry. Currently, blood cell images become predominantly valuable in medical diagnostics tools. In this paper, we present an adaptive hybrid analysis based on selected segmentation algorithms. Three designates common approaches, that are Fuzzy c-means, K-means and Mean-shift are adapted. Blood cell images that are infected with malaria parasites at various stages were tested. The most suitable method will be selected based on the lowest number of regions. The selected approach will be enhanced by applying Median-cut algorithm to further expand the segmentation process. The proposed adaptive hybrid method has shown a significant improvement in the number of regions.

scholarly journals Natural image segmentation based on mutual information

2020 ◽  
Vol 309 ◽  
pp. 03030
Author(s):  
Yiwei Zhu
Keyword(s):  
Image Segmentation ◽  
Mutual Information ◽  
Energy Difference ◽  
Experimental Results ◽  
Natural Image ◽  
Segmented Image ◽  
Segmentation Algorithms ◽  
Boundary Fitting ◽  
Fitting In ◽  
Unsupervised Image Segmentation

Natural image segmentation plays an important role in the fields of image processing and computer vision. Image segmentation based on clustering is an important method in unsupervised image segmentation algorithms. But there are two problems with this type of approach. First, feature extraction is generally pixel-based, which results in poor segmentation results and boundary fitting. In order to solve this problem, it is proposed to introduce super pixel to be segmented image preprocessing. Second, the number of partitions is difficult to determine. Aiming at this problem, an energy difference based on mutual information is proposed, which can automatically determine the number of partitions. The experimental results on the standard database show that the proposed algorithm overcomes the above problems and achieves better experimental results.

Remote Sensing Image Segmentation Based on Improved Statistical Region Merging

2014 ◽  
Vol 667 ◽  
pp. 226-229
Author(s):  
Xiu Li Gong ◽  
Zhi Ming Wang
Keyword(s):  
Remote Sensing ◽  
Image Segmentation ◽  
Remote Sensing Image ◽  
Segmentation Algorithm ◽  
Region Merging ◽  
Gradient Estimation ◽  
Coarse To Fine ◽  
Statistical Region Merging ◽  
Image Segmentation Algorithm ◽  
Dissimilarity Criterion

Statistical Region Merging (SRM) is an efficient image segmentation algorithm for images with noise and partial occlusion. However, due to the complexity of remote sensing image, SRM can’t give satisfactory results. This paper proposes an improved image segmentation algorithm for remote sensing image based on SRM. Firstly, 8-connexity gradient estimation models are used to obtain more precisely edges. Secondly, the dissimilarity criterion between regions is replaced by a normalized distance standard. Finally, it dynamically updates and sorts dissimilarity between regions during region merging. Experimental results show the proposed algorithm can achieve better segmentation results from coarse to fine compared with original SRM.

Sign in / Sign up

Export Citation Format

Share Document