【摘要】：將引導(dǎo)濾波與提升小波相結(jié)合提出了一種多尺度引導(dǎo)濾波方法,以實(shí)現(xiàn)在平滑圖像細(xì)節(jié)的同時(shí)保持圖像邊緣不模糊。該方法通過提升小波法對(duì)將圖像進(jìn)行多尺度分解,即將信號(hào)分解成一個(gè)低頻子帶和多個(gè)高頻子帶。在提升小波重構(gòu)過程中,利用引導(dǎo)濾波平滑每個(gè)尺度的低頻信息并保持其邊緣不模糊。最后,針對(duì)濾波后殘余的細(xì)節(jié),對(duì)提升小波重構(gòu)后的平滑圖像再次進(jìn)行引導(dǎo)濾波,以便進(jìn)一步平滑圖像細(xì)節(jié)。將多尺度引導(dǎo)濾波應(yīng)用于暗通道去霧先驗(yàn)理論并進(jìn)行了主、客觀評(píng)價(jià)。結(jié)果顯示:多尺度引導(dǎo)濾波能夠深層次平滑圖像細(xì)節(jié),保持邊緣完整性,從整體上提高了圖像的對(duì)比對(duì)和視覺效果,有效恢復(fù)了場(chǎng)景信息并保留場(chǎng)景的邊緣信息。另外,該方法改善了客觀評(píng)價(jià)指標(biāo),其對(duì)比度增強(qiáng)系數(shù)指標(biāo)平均提升了0.1以上,場(chǎng)景結(jié)構(gòu)相似度平均提升了1以上,而LOE(Lightness Order Error)參數(shù)降低了10以上,滿足了去霧應(yīng)用的視覺需求。
[Abstract]:A multi-scale guided filtering method is proposed by combining the bootstrapping filter with lifting wavelet in order to smooth the image details while keeping the edge of the image not blur. This method decomposes the image into one low frequency subband and several high frequency subbands by lifting wavelet method. In the process of lifting wavelet reconstruction, the low frequency information of each scale is smoothed by guided filter and its edge is not blurred. Finally, according to the residual details of the filter, the smooth image reconstructed by lifting wavelet is guided again to further smooth the image details. The multiscale guided filter is applied to the priori theory of defogging in dark channels and the subjective and objective evaluation is carried out. The results show that the multi-scale guided filter can smooth the details of the image at a deep level, maintain the edge integrity, improve the contrast and visual effect of the image, restore the scene information and retain the edge information of the scene effectively. In addition, the objective evaluation index is improved, the contrast enhancement coefficient is improved more than 0.1 on average, the scene structure similarity is improved by more than 1 on average, and the LOE (Lightness Order Error) parameter is reduced by more than 10, which meets the visual requirement of defog application.
【作者單位】： 中國(guó)科學(xué)院長(zhǎng)春光學(xué)精密機(jī)械與物理研究所;中國(guó)科學(xué)院大學(xué);
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(No.61401425)
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 許微;侯正信;;鄰域擴(kuò)散選擇平滑圖像放大算法[J];光電子.激光;2007年06期

2 劉鐵根;鄧集杰;張忠傳;朱均超;何瑾;李秀艷;;基于平滑卷積定位的圓形印鑒提取方法研究[J];光電工程;2009年04期

3 周昌雄;蘇品剛;馬國(guó)軍;;基于局部方差的自蛇模型平滑毫米波圖像[J];微電子學(xué)與計(jì)算機(jī);2011年10期

4 蔣愛德;陳炎龍;;圖像中邊緣信號(hào)高斯平滑后的偏移問題[J];計(jì)算機(jī)系統(tǒng)應(yīng)用;2012年12期

相關(guān)碩士學(xué)位論文 前2條

1 鄭建勛;擴(kuò)散平滑模型在Tina平臺(tái)上的實(shí)現(xiàn)和應(yīng)用[D];暨南大學(xué);2006年

2 石曉紅;基于三維柵格平滑的圖像增強(qiáng)方法研究與應(yīng)用[D];中山大學(xué);2011年

，

本文編號(hào)：2276073