發(fā)布時間：2019-01-07 20:39

【摘要】：圖像的多尺度分解技術(shù)和融合規(guī)則是決定多聚焦圖像融合效果的關(guān)鍵因素。k次W系是一類以k次多項式和k次分段多項式為基函數(shù)的新的混合正交函數(shù)系統(tǒng),對應(yīng)的W變換是一種具有正交性和精確重構(gòu)性的有效多分辨分析工具。結(jié)合W變換的多尺度特點和非子采樣方向濾波器組變換的多方向性,提出了一種新的基于W變換和非子采樣方向濾波器組(NSDFB)的多尺度多方向變換。該變換利用W變換對圖像進行多尺度分解,利用二維NSDFB對W分解的高頻子帶系數(shù)進行方向分解,得到不同尺度不同方向的子帶圖像。在此基礎(chǔ)上,提出了一種新的多聚焦圖像融合算法。該算法針對多聚焦圖像高頻系數(shù)的特點,改進了常用簡化脈沖耦合神經(jīng)網(wǎng)絡(luò)算法,并將其用于高頻系數(shù)的融合規(guī)則中。實驗結(jié)果表明,提出的融合方法能夠有效地選擇源圖像中的聚焦良好區(qū)域,抑制偽影信息,產(chǎn)生視覺效果更好的融合圖像,且在標準差、信息熵、平均梯度和空間頻率等客觀評價指標上都優(yōu)于傳統(tǒng)的基于Contourlet變換、非下采樣Contourlet變換、離散小波變換的融合方法。
[Abstract]:The multi-scale decomposition technique and fusion rules are the key factors to determine the fusion effect of multi-focus image. The k-degree W system is a new hybrid orthogonal function system with the k-degree polynomial and the k-degree piecewise polynomial as the basis functions. The corresponding W transform is an effective multi-resolution analysis tool with orthogonality and precision reconstruction. Based on the multi-scale characteristic of W transform and the multi-directivity of non-subsampling directional filter bank transform, a new multi-scale multi-directional transformation based on W transform and (NSDFB) is proposed. The transform uses W transform to decompose the image in multi-scale, and two-dimensional NSDFB to decompose the high-frequency subband coefficients of W decomposition in the direction, and obtain the sub-band images with different scales and different directions. On this basis, a new multi-focus image fusion algorithm is proposed. According to the characteristics of high frequency coefficients of multi-focus images, this algorithm improves the common simplified pulse coupling neural network algorithm, and applies it to the fusion rules of high frequency coefficients. The experimental results show that the proposed fusion method can effectively select a good focus area in the source image, suppress the artifacts, and produce a better fusion image with better visual effect, and at the standard deviation, the information entropy, The average gradient and spatial frequency are superior to the traditional fusion methods based on Contourlet transform, non-downsampling Contourlet transform and discrete wavelet transform.
【作者單位】： 北京林業(yè)大學(xué)理學(xué)院;
【基金】：國家自然科學(xué)基金(61571046,61372190,61370193)資助項目
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前9條

1 曹風(fēng)云;趙凱;王筱薇倩;錢言玉;王浩;;自適應(yīng)水下彩色圖像增強算法[J];電子測量與儀器學(xué)報;2016年05期

2 李萍;張波;尚怡君;;基于紅外圖像和特征融合的飛機目標識別方法[J];電光與控制;2016年08期

3 閆光豹;李開宇;楊盛亞;;基于FPGA的紅外和CCD圖像融合研究及實現(xiàn)[J];電子測量技術(shù);2015年06期

4 劉斌;喬雙梁;魏艷萍;;基于采樣三通道不可分小波的多光譜圖像融合[J];儀器儀表學(xué)報;2015年03期

5 肖進勝;饒?zhí)煊?賈茜;宋金鐘;易本順;;基于圖切割的拉普拉斯金字塔圖像融合算法[J];光電子.激光;2014年07期

6 楊勇;鄭文娟;黃淑英;方志軍;袁非牛;;人眼視覺感知特性的非下采樣Contourlet變換域多聚焦圖像融合[J];中國圖象圖形學(xué)報;2014年03期

7 許良鳳;林輝;胡敏;;基于差分進化算法的多模態(tài)醫(yī)學(xué)圖像融合[J];電子測量與儀器學(xué)報;2013年02期

8 郭雷;程Xh;趙天云;;基于小波變換和鄰域特征的多聚焦圖像融合算法[J];西北工業(yè)大學(xué)學(xué)報;2011年03期

9 張寅s，

本文編號：2404136