基于图像矫正与小波变换融合的岩心图像拼接算法  

Core image splicing algorithm based on image correction and wavelet transform fusion

作　　者：陈潇逸 滕奇志[1] 何海波 王正勇[1] 吴晓红[1] CHEN Xiaoyi;TENG Qizhi;HE Haibo;WANG Zhengyong;WU Xiaohong(College of Electronic and Information Engineering,Sichuan University,Chengdu 610065,China;Chengdu Xitu Technology Co.,Ltd.,Chengdu 610065,China)

机构地区：[1]四川大学电子信息学院,成都610065 [2]成都西图科技有限公司,成都610065

出　　处：《智能计算机与应用》2024年第3期21-27,共7页Intelligent Computer and Applications

基　　金：国家自然科学基金(62071315)。

摘　　要：为了提高岩心图像拼接的效率,针对在岩心采集出现的图像中的像素错位现象以及图像拼接处理出现的亮度差异、鬼影等问题,提出基于图像矫正与小波变换融合的岩心图像融合算法。首先改进AKAZE算法提高提取效率,对采集图像进行图像矫正得到矫正图像;再对矫正后的待拼接图像进行特征点提取与匹配,得到2幅图像之间配准关系;最后通过基于HSI域的小波融合与改进最佳缝合线融合得到拼接图像。实验结果表明,本文提出的矫正与拼接算法满足实际需求,图像无明显上下拼接缝与错位,且在DoEM和PSNR指标上与传统最佳缝合线和改进的渐入渐出算法相比均有所提升,融合区域避免了鬼影且亮度过渡均匀,无明显左右缝合线产生,拼接的图像符合人眼视觉。In order to improve the efficiency of core image stitching,aimed at the problems of pixel misalignment in the core images and brightness differences in stitching processing,the paper proposes a core image fusion algorithm based on image correction and wavelet transform fusion.Firstly,the AKAZE algorithm is improved to improve the extraction efficiency,and the image correction is performed to obtain the corrected image,then the feature points are extracted and matched between the left and right images to obtain the alignment relationship between the two images,finally the stitched image is obtained by the wavelet fusion based on the HSI domain and the improved best suture fusion.The experimental results show that the correction and stitching algorithm proposed in this paper meets the practical requirements,and the image has no obvious top and bottom stitching and misalignment,and the DoEM and PSNR indexes are improved compared with the other two algorithms,the fusion area avoids ghosting and the brightness transition is uniform without obvious left and right stitching lines,and the stitched images meet the human eye vision.

关 键 词：岩心图像 图像矫正 AKAZE 小波变换 最佳缝合线 图像拼接 

分 类 号：TP399[自动化与计算机技术—计算机应用技术]