[1]孙登第 卜令斌 赵海峰 罗斌.基于梯度相似性与Rényi熵图的图像配准算法[J].计算机技术与发展,2012,(12):97-100.
 SUN Deng-di,BU Ling-bin,ZHAO Hai-feng,et al.Image Registration Based on Rényi Entropic Graph Combined with Gradient Similarity[J].,2012,(12):97-100.
点击复制

基于梯度相似性与Rényi熵图的图像配准算法()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2012年12期
页码:
97-100
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Image Registration Based on Rényi Entropic Graph Combined with Gradient Similarity
文章编号:
1673-629X(2012)12-0097-04
作者:
孙登第12 卜令斌1 赵海峰12 罗斌12
[1]安徽大学计算机科学与技术学院[2]安徽工业图像处理与分析重点实验室
Author(s):
SUN Deng-diBU Ling-bin ZHAO Hai-feng LUO Bin
[1]School of Computer Science and Technology, Anhui University[2]Industrial Image Processing & Analysis Key Lab of Anhui Province
关键词:
图像配准广义近邻图Rényi熵图梯度相似性
Keywords:
image registrationgeneralized nearest-neighbor graph Rényi entropy graphgradient similarity
分类号:
TP391
文献标志码:
A
摘要:
图像配准技术是图像处理与分析中的基本任务。针对图像配准对鲁棒性强、准确性高和速度快的要求,文中提出一种基于梯度相似性与Rényi熵图的图像配准算法。该算法首先提取图像特征点集,以Rényi互信息作为目标函数,然后使用特征点集的广义近邻图来估计Rényi熵与互信息,最后将特征点梯度信息融入到配准框架中。新算法结合了特征点梯度信息的鲁棒性和Rényi熵图理论的高效性。在真实遥感图像上进行的配准的实验表明,与传统方法相比,新算法在鲁棒性、速度和准确度上都达到很好的结果,是一种有效的图像配准方法
Abstract:
Image registration technology is the basic task in image processing and analysis. Aiming at the requirements of good robustness, high accuracy and fast speed for image registration, propose an algorithm for image registration based on gradient similarity and Rényi en tropic graph. The algorithm extracts the feature points from images firstly, set the Rényi mutual information as the object function. Then use the generalized nearest-neighbor graph to estimate the Rényi entropy and mutual information. At last, the gradient information be tween images is integrated into the registration framework. The algorithm combined with the robustness of feature points and the high efficiency of using Rényi entropic graph to estimate the Rényi entropy. The experimental results show that for the real-world remote sensing images, the proposed algorithm can achieve better robustness, higher speed and better accuracy than the traditional methods. It is an effec tive image registration method

相似文献/References:

[1]焦晶萍 廖文和 沈建新.一种基于模板匹配法的眼底图像拼接方法[J].计算机技术与发展,2010,(04):148.
 JIAO Jing-ping,LIAO Wen-he,SHEN Jian-xin.A Fundus Image Mosaic Method Based on Template Matching[J].,2010,(12):148.
[2]翟利志 王敬东 李鹏.基于邻域信息的红外与可见光图像互信息配准[J].计算机技术与发展,2008,(10):151.
 ZHAI Li-zhi,WANG Jing-dong,LI Peng.Infrared and Visible Light Image Mutual Information Registration Based on Neighborhood Information[J].,2008,(12):151.
[3]冯林 颜世鹏 孙焘.图像配准中的一种特定区域轮廓提取算法[J].计算机技术与发展,2006,(03):11.
 FENG Lin,YAN Shi-peng,SUN Tao.A Contour Extraction Algorithm of Special Region in Image Registration[J].,2006,(12):11.
[4]邰伟鹏 栾干 岳建华[].基于轮廓特征匹配的数字人多模态图像配准[J].计算机技术与发展,2006,(07):186.
 TAI Wei-peng,LUAN Gan,YUE Jian-hua.Image Registration Among Multimodal Medical Based on Matching of Contour Characteristic[J].,2006,(12):186.
[5]吴福虎 罗斌 汤进 杨龙.基于边缘相关的红外热像配准[J].计算机技术与发展,2012,(07):88.
 WU Fu-hu,LUO Bin,TANG Jin,et al.Infrared Image Registration Based on Edge Correlation[J].,2012,(12):88.
[6]丁南南.墨西哥帽小波和归一化伪Zernike矩的图像配准[J].计算机技术与发展,2014,24(04):72.
 DING Nan-nan.Image Registration Based on Mexican-hat Wavelets and Normalized Pseudo-Zernike Moments[J].,2014,24(12):72.
[7]王凤娇,陈光化,周文. 基于SIFT的POCS图像超分辨率重建[J].计算机技术与发展,2014,24(11):39.
 WANG Feng-jiao,CHEN Guang-hua,ZHOU Wen. Multi-frame Image Super-resolution Reconstruction Based on SIFT[J].,2014,24(12):39.
[8]雷飞,王文学,王雪丽,等. 基于改进SURF的实时视频拼接方法[J].计算机技术与发展,2015,25(03):32.
 LEI Fei,WANG Wen-xue,WANG Xue-li,et al. Real-time Video Stitching Method Based on Improved SURF[J].,2015,25(12):32.
[9]张凯[],杨红雨[][],兰时勇[][].基于CUDA的SIFT特征与拼接缝的全景图生成[J].计算机技术与发展,2015,25(09):22.
 ZHANG Kai[],YANG Hong-yu[][],LAN Shi-yong[][]. Panorama Generation of SIFT and Stitch Line Based on CUDA[J].,2015,25(12):22.
[10]袁媛,滕奇志,何小海,等.岩石薄片图像拼接中的色差校正算法[J].计算机技术与发展,2018,28(07):1.[doi:10.3969/ j. issn.1673-629X.2018.07.001]
 YUAN Yuan,TENG Qi-zhi,HE Xiao-hai,et al. Chromatic Aberration Correction Algorithm for Splicing of Rock Slice[J].,2018,28(12):1.[doi:10.3969/ j. issn.1673-629X.2018.07.001]

备注/Memo

备注/Memo:
国家自然科学基金(61073116,61003131);安徽省自然科学基金项目(1208085MFl09)孙登第(1983-),男,安徽淮南人,博士研究生,研究方向为图像处理、模式识别、随机图论;罗斌,教授,博士生导师,研究方向为图像处理、模式识别、数据挖掘
更新日期/Last Update: 1900-01-01