scholarly journals Cross Entropy: A New Solver for Markov Random Field Modeling and Applications to Medical Image Segmentation

2005 ◽  
pp. 229-237 ◽  
Author(s):  
Jue Wu ◽  
Albert C. S. Chung
Keyword(s):  
Image Segmentation ◽  
Random Field ◽  
Markov Random Field ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Cross Entropy ◽  
Field Modeling ◽  
Markov Random

scholarly journals Image Segmentation of Printed Fabrics with Hierarchical Improved Markov Random Field in the Wavelet Domain

2016 ◽  
Vol 11 (3) ◽  
pp. 155892501601100 ◽  
Author(s):  
Junfeng Jing ◽  
Qi Li ◽  
Pengfei Li ◽  
Hongwei Zhang ◽  
Lei Zhang
Keyword(s):  
Image Segmentation ◽  
Random Field ◽  
Markov Random Field ◽  
Field Model ◽  
Wavelet Domain ◽  
Hybrid Schemes ◽  
Markov Random Field Model ◽  
Field Modeling ◽  
Markov Random ◽  
Maximum A Posterior

An improved MRF algorithm–hierarchical Gauss Markov Random Field model in the wavelet domain is presented for fabric image segmentation in this paper, which obtains the relation of inter-scale dependency from the feature field modeling and label field modeling. The Gauss-Markov random field modeling is usually adopted to feature field modeling. The label field modeling employs the inter-scale causal MRF model and the intra-scale non-causal MRF model. After that, parameter estimation is the essential section in the inter-scale, enhancing modeling capabilities of the pixels partial dependency. Sequential maximum a posterior criterion is applied to achieve the results of image segmentation. Comparisons with other hybrid schemes, results are indicated that performance of the presented algorithm is effective and accurate, in terms of classification accuracy and kappa coefficient, for patterned fabric images.

A Densely Connected Network Based on U-Net for Medical Image Segmentation

2021 ◽  
Vol 17 (3) ◽  
pp. 1-14
Author(s):  
Zhenzhen Yang ◽  
Pengfei Xu ◽  
Yongpeng Yang ◽  
Bing-Kun Bao
Keyword(s):  
Feature Extraction ◽  
Image Segmentation ◽  
Loss Function ◽  
Network Architecture ◽  
Medical Image ◽  
Medical Image Segmentation ◽  
Cross Entropy ◽  
Loss Functions ◽  
Feature Maps ◽  
Different Levels

The U-Net has become the most popular structure in medical image segmentation in recent years. Although its performance for medical image segmentation is outstanding, a large number of experiments demonstrate that the classical U-Net network architecture seems to be insufficient when the size of segmentation targets changes and the imbalance happens between target and background in different forms of segmentation. To improve the U-Net network architecture, we develop a new architecture named densely connected U-Net (DenseUNet) network in this article. The proposed DenseUNet network adopts a dense block to improve the feature extraction capability and employs a multi-feature fuse block fusing feature maps of different levels to increase the accuracy of feature extraction. In addition, in view of the advantages of the cross entropy and the dice loss functions, a new loss function for the DenseUNet network is proposed to deal with the imbalance between target and background. Finally, we test the proposed DenseUNet network and compared it with the multi-resolutional U-Net (MultiResUNet) and the classic U-Net networks on three different datasets. The experimental results show that the DenseUNet network has significantly performances compared with the MultiResUNet and the classic U-Net networks.

Color Image Segmentation Using Entropy of Fuzziness and Markov Random Field

1997 ◽  
Vol 30 (7) ◽  
pp. 269-274
Author(s):  
R. Boussarsar ◽  
P. Martin ◽  
R. Lecordier ◽  
M. Ketata
Keyword(s):  
Image Segmentation ◽  
Random Field ◽  
Markov Random Field ◽  
Color Image ◽  
Color Image Segmentation ◽  
Markov Random
Sign in / Sign up

Export Citation Format

Share Document