崔洪刚,唐浩,汪永超.基于显著计算与变分法的多尺度图像融合[J].电视技术,2016,40(12):17-22
基于显著计算与变分法的多尺度图像融合
A multiscale image fusion based on saliency computation and total variation
投稿时间:2016-03-30  最后修改时间:2016-05-25
DOI:10.16280/j.videoe.2016.12.004
中文关键词:  多尺度变换  显著计算  变分法  图像融合
英文关键词:multiscale transformation  saliency computation  total variation  image fusion
基金项目:广东省科技计划:河源市优势产业标准信息服务共享平台研究(2015A040405007)
        
作者单位
崔洪刚 广东工业大学计算机学院
唐浩 河源广工大协同创新研究院
汪永超 河源广工大协同创新研究院
摘要点击次数: 160
全文下载次数: 1
中文摘要:
      在多尺度图像融合中,通常将图像进行多尺度变换,再对变换后的低频系数与高频系数采用一定的融合规则进行融合,然而融合规则的选择将影响图像的清晰度与融合质量。本文将视觉显著模型与变分法理论应用在多尺度图像的低频系数融合中,获取最优的融合系数组合,从而增强融合效果,通过对红外线与可见光图像、医学图像的融合实验表明,本文方法能克服融合图像对比度偏低的缺陷,获取的图像能较好保留源图像的显著目标信息,如形状、大小、色调、纹理等,特别是针对异源亮度差异较大的图像。在主观视觉感受与客观评价指标上都有所提升。
英文摘要:
      In the image fusion methods based on multiscale transform, the coefficients of low and high frequency are fused through a weighted sum rule . The choosing of weight function inflluwences definition and quality of fused image. A novel method was proposed for the optimization of low weight function based on total variation and visual saliency to obtain eventual fused image.Experimental. Image Fusion experiments are carried out utilize visible light images and medical images that is registration processed.Result shows that the proposed method can overcome the low image contrast problem, and the reconstructed image protects salient-object information , such as shape, size, color, texture, etc effectively, and it is more effective for processing source images with brightness differences. The subjective visual perception and objective evaluation index has got certain improvement..
查看全文  查看/发表评论  下载PDF阅读器
关闭