High performance local-texture-information weighted SAR template image matching

2013 ◽  
Author(s):  
Qiuze Yu ◽  
Guangzhou Qu ◽  
Yan Zhang ◽  
Yufan Wang
Keyword(s):  
Image Matching ◽  
High Performance ◽  
Local Texture ◽  
Texture Information ◽  
Template Image

scholarly journals Robust Multisensor Image Matching Using Bayesian Estimated Mutual Information

2013 ◽  
Vol 2013 ◽  
pp. 1-11
Author(s):  
Lurong Shen ◽  
Xinsheng Huang ◽  
Yuzhuang Yan ◽  
Yongbin Zheng ◽  
Wanying Xu
Keyword(s):  
Mutual Information ◽  
Cost Saving ◽  
Image Matching ◽  
Prior Information ◽  
Kernel Density ◽  
Density Estimate ◽  
Kernel Density Estimate ◽  
Template Image ◽  
Matching Performance

Mutual information (MI) has been widely used in multisensor image matching, but it may lead to mismatch among images with messy background. However, additional prior information can be of great help in improving the matching performance. In this paper, a robust Bayesian estimated mutual information, named as BMI, for multisensor image matching is proposed. This method has been implemented by utilizing the gradient prior information, in which the prior is estimated by the kernel density estimate (KDE) method, and the likelihood is modeled according to the distance of orientations. To further improve the robustness, we restrict the matching within the regions where the corresponding pixels of template image are salient enough. Experiments on several groups of multisensor images show that the proposed method outperforms the standard MI in robustness and accuracy and is similar with Pluim’s method. However, our computation is far more cost saving.

Artificial Fish Swarm Algorithm Based on Fast Image Matching

2011 ◽  
Vol 271-273 ◽  
pp. 297-302
Author(s):  
Miao Ma ◽  
Jiao He ◽  
Min Guo
Keyword(s):  
Image Matching ◽  
Feature Matching ◽  
Fitness Function ◽  
Optimal Solution ◽  
Fast Method ◽  
Artificial Fish Swarm Algorithm ◽  
Template Image ◽  
Artificial Fish Swarm ◽  
Swarm Algorithm ◽  
Exclusive Or

Due to the large amount of calculation and high time-consuming in traditional grayscale matching, this paper combines artificial fish algorithm of swarm intelligence with edge detection and the operation of bitwise exclusive or, and presents a fast method on feature matching. The method regards the problem of image matching as a process of searching the optimal solution. In order to provide artificial fish swarm algorithm with an appropriate fitness function, the operation of bitwise exclusive or and addition is employed to deal with the edge information extracted from the template image and the searching image. Then the best matching position is gradually approaching by swarming, following and other behaviors of artificial fish. Experimental results show that the proposed method not only significantly shortens the matching time and guarantees the matching accuracy, but also is robust to noise disturbance.

Image Matching Application Based on Modified SURF Algorithm

2013 ◽  
Vol 423-426 ◽  
pp. 2591-2596
Author(s):  
Zhen Yuan Ma ◽  
Shi Xu Shi ◽  
Li Xian Yuan ◽  
Pei Chang Gu ◽  
Han Huang
Keyword(s):  
Critical Points ◽  
Image Matching ◽  
High Performance ◽  
Rejection Rate ◽  
Detection Algorithm ◽  
Test Paper ◽  
Matching Accuracy ◽  
False Rejection Rate ◽  
Modified Algorithm ◽  
False Rejection

The key technique to increase the accuracy of electronic marking is the technique of image matching, namely to match two doubtfully duplicate images. Currently there are few technologies aiming for features on test paper images with high performance on matching accuracy. The research is based on SURF algorithm and specific to the features of test paper images. Thus the research is to put forward the modified algorithm with constraints among feature spots of orientation angles on their geometrical positions, including differential constraints on critical points from approximate blank test papers with less individual features at the same time. After processing and analyzing 2,000 test paper gathered from one actual examination, the results show that the modified detection algorithm has 100% false rejection rate and 100% accuracy when it is used to detect the test paper matching.

A Multi-Scale Image Matching Recognition Algorithm Based on Phase Correlation

2011 ◽  
Vol 301-303 ◽  
pp. 1438-1443
Author(s):  
Yong Gang Tian ◽  
Min Gang Wang ◽  
Ying Ping Fan
Keyword(s):  
Image Matching ◽  
Recognition Algorithm ◽  
Phase Correlation ◽  
Reference Image ◽  
Recognition Method ◽  
Multi Scale ◽  
Template Image ◽  
The Fourier Transform ◽  
Template Size ◽  
Traditional Image

The image matching recognition method of phase correlation is based on the shift characteristics of the Fourier transform. The traditional image matching recognition algorithm has significant influence of the template size upon its matching accuracy and has weak resilience to noises except for the gauss noise. Addressing these shortcomings, we proposed a multi-scale matching recognition method based on phase correlation, combined with wavelet transform and edge detection. The algorithm, processed the reference image and the template image in different scales with such steps: decomposition, denoising, reconstruction, edge detection and the Fourier transform, phase correlation. Hence, it overcome the dependence upon template size effectively and improve the reliability and the resilience of various noises. Finally, we verified the algorithm with a real ground shooting image as the reference image and an intercepted part as the template image. The results have shown that the proposed approach is better than the traditional image matching method.

Sign in / Sign up

Export Citation Format

Share Document