激光与光电子学进展, 2018, 55 (1): 011011, 网络出版: 2018-09-10   

基于熵率分割和多尺度分解的图像融合方法 下载: 1037次

Image Fusion Method Based on Entropy Rate Segmentation and Multi-Scale Decomposition
作者单位
河南大学计算机与信息工程学院, 河南 开封 475001
摘要
为了提高多聚焦融合技术中融合图像系数间的相关性,增强区域信息丰富度,提出一种基于熵率分割和多尺度分解的多聚焦图像融合方法。利用多尺度分解后边缘和细节信息保存在高频子带这一特征,通过模值比较和一致性检测,可以更好地保留图像的细节;同时结合低频子带与熵率分割,把图像中相近的信息系数分到同一个区域中,再根据区域空间频率和能量融合图像,提高系数间的相关性,使得融合图像边缘过渡更加自然;最后,对图像进行逆变换得到融合结果图。实验结果表明,本文方法在主客观评价中都具有较好的表现,能够得到较好的融合效果,适用性高。
Abstract
In order to improve the correlation of the fusion coefficients in multi-focus image fusion technology and enhance regional information abundance, we propose a method based on the entropy rate segmentation and multi-scale decomposition on multi-focus image fusion. After multi-scale decomposition, the edge and detail information are stored in the high frequency subband. We can better preserve the details of the image through model value and comparison consistency check. At the same time, the similar information coefficients of image are assigned to the same area, combined with low frequency subband and entropy rate segmentation. Then the image is fused according to the regional spatial frequency and energy, the correlation of the coefficients is improved, and the fusion image edge transition is more natural. Finally, the inverse transformation is carried out on the images to get the fusion results. Experimental results show that the proposed method has better performance in both subjective and objective evaluation, and achieves better fusion effect with high applicability.

殷向, 马骏. 基于熵率分割和多尺度分解的图像融合方法[J]. 激光与光电子学进展, 2018, 55(1): 011011. Yin Xiang, Ma Jun. Image Fusion Method Based on Entropy Rate Segmentation and Multi-Scale Decomposition[J]. Laser & Optoelectronics Progress, 2018, 55(1): 011011.

本文已被 2 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!