基于栈式自编码网络的非线性变化灰度差异图像配准  

Nonlinear Grayscale Difference Image Registration Based on Stacked Autoencoder Network

作　　者：黄超[1] 郭浩[1] 高岩 安居白[1] Huang Chao;Guo Hao;Gao Yan;An Jubai(College of Information Science and Technology,Dalian Maritime University,Dalian,Liaoning 116026,China)

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026

出　　处：《激光与光电子学进展》2021年第16期225-231,共7页Laser & Optoelectronics Progress

基　　金：中国国家海洋局的海洋非营利性行业研究专项(2013418025)。

摘　　要：光照或成像条件等因素会引起图像间的非线性变化灰度差异,导致图像的匹配效果较差。针对该问题,提出了一种基于栈式自编码(SAE)网络和结合圆形、线形邻域的局部二值模式(CL-LBP)特征描述子的非线性变化灰度差异图像配准算法。首先,结合改进的局部纹理算子与区域特征提取CL-LBP特征描述子并进行匹配。然后,采用监督学习分类的方式消除误匹配。最后,通过SAE网络对构建的匹配表示进行训练,提取匹配表示的深度特征并接入Logistic分类层进行分类。实验结果表明,该算法对非线性变化灰度差异图像的匹配精度较高,且在实际海冰图像中的匹配效果也较好。Factors such as illumination or imaging conditions can cause a nonlinear grayscale difference between images,resulting in poor matching of images.To solve this problem,this paper proposes a new image registration algorithm based on the stacked autoencoder(SAE)network and local binary pattern with a circular and linear neighborhood(CL-LBP).First,the CL-LBP feature descriptor is extracted and matched by combining the improved local texture operator with the regional feature.Then,the supervised learning classification method is used to eliminate mismatches.Finally,the constructed matching representation is trained using the SAE network and the depth features of the matching representation are extracted and connected to a logistic classification layer to classify the matching pairs.The experimental results show that the algorithm has good matching accuracy in matching the nonlinear grayscale difference images.Moreover,it has a good matching effect in the actual sea ice images.

关 键 词：图像处理 图像配准 特征提取 栈式自编码 非线性变化灰度差异 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]