本文選題：圖像修復(fù) + 置信項(xiàng)��； 參考：《中國(guó)圖象圖形學(xué)報(bào)》2017年09期

【摘要】：目的針對(duì)基于樣本塊的Criminisi圖像修復(fù)算法易發(fā)生置信項(xiàng)迅速下降趨于零,使優(yōu)先權(quán)計(jì)算公式失效,導(dǎo)致修復(fù)順序錯(cuò)亂造成的修復(fù)效果失真問(wèn)題,以及在搜索匹配塊時(shí)存在的搜索范圍過(guò)大,效率過(guò)低,易出現(xiàn)匹配到不符合視覺(jué)效果的紋理塊問(wèn)題,提出一種基于優(yōu)先權(quán)改進(jìn)和塊劃分的圖像修復(fù)算法。方法首先重新定義優(yōu)先權(quán)中的置信項(xiàng),用樣本塊中的棋盤(pán)距離替代原計(jì)算公式,保證優(yōu)先權(quán)一直發(fā)揮作用,從而減少因修復(fù)順序不合理造成的錯(cuò)誤匹配;其次根據(jù)圖像紋理信息將其自適應(yīng)劃分為不同大小的圖像塊,使待修復(fù)樣本塊只在具有相似特征的圖像塊區(qū)域內(nèi)搜索匹配。結(jié)果實(shí)驗(yàn)結(jié)果表明,新定義的優(yōu)先權(quán),保證了修復(fù)算法的正常進(jìn)行,改善了修復(fù)圖像的視覺(jué)效果;由圖像自適應(yīng)塊劃分引導(dǎo)匹配過(guò)程,可使匹配在更少的候選塊中進(jìn)行,提高了算法速度。將本文方法與3種全局搜索匹配方法和1種局部搜索匹配方法進(jìn)行修復(fù)結(jié)果對(duì)比分析,本文方法的修復(fù)結(jié)果視覺(jué)完整性較好,而且修復(fù)時(shí)間小于其中3種算法。結(jié)論通過(guò)改進(jìn)Criminisi算法優(yōu)先權(quán)中的置信項(xiàng),避免因其趨于零導(dǎo)致的修復(fù)順序錯(cuò)亂造成的錯(cuò)誤累積情況的發(fā)生;同時(shí)通過(guò)改進(jìn)待修復(fù)匹配塊的搜索范圍,對(duì)整幅圖像進(jìn)行自適應(yīng)塊劃分,使搜索只在相似塊中進(jìn)行,不僅減少了時(shí)間,而且提高了匹配的準(zhǔn)確性。本文方法對(duì)于自然圖像中大面積目標(biāo)物體移除方面有較好的應(yīng)用,可獲得較滿意的修復(fù)效果。
[Abstract]:Aim to solve the problem that Criminisi image restoration algorithm based on sample block is prone to rapidly decrease the confidence item to zero, make the priority calculation formula invalid, and lead to the distortion of the repair effect caused by the repair sequence disorder. And when searching matching blocks, the search range is too large, the efficiency is too low, and the texture blocks are easily matched to the visual effect. An image restoration algorithm based on priority improvement and block partitioning is proposed. Methods firstly, the confidence items in priority are redefined, and the original calculation formula is replaced by the chessboard distance in the sample block, so as to ensure that priority always plays a role, so as to reduce the mismatch caused by the unreasonable repair sequence. Secondly, according to the texture information of the image, it is adaptively divided into different size image blocks, so that the sample blocks to be repaired only search for matching in the image blocks with similar characteristics. Results the experimental results show that the new definition of priority ensures the normal implementation of the restoration algorithm and improves the visual effect of the restored image, and that the matching process can be guided by image adaptive block partitioning, so that the matching can be carried out in fewer candidate blocks. The algorithm speed is improved. Compared with three global search matching methods and one local search matching method, the results obtained in this paper have better visual integrity, and the repair time is less than that of the three algorithms. Conclusion by improving the confidence items in the priority of the Criminisi algorithm, we can avoid the accumulation of errors caused by the repair order disorder caused by its tendency to zero, and improve the search range of the matching blocks to be repaired. The adaptive block partition of the whole image makes the search only in the similar block, which not only reduces the time, but also improves the accuracy of matching. This method has a good application in the removal of large area objects in natural images and can obtain satisfactory results.
【作者單位】： 南昌航空大學(xué)計(jì)算機(jī)視覺(jué)研究所;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61165011,61662049)~~
【分類號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 于文靜;楊富琴;馮偉國(guó);;圖像修復(fù)實(shí)驗(yàn)的設(shè)計(jì)[J];實(shí)驗(yàn)室研究與探索;2012年06期

2 徐冬青;;計(jì)算機(jī)圖像修復(fù)技術(shù)[J];計(jì)算機(jī)光盤(pán)軟件與應(yīng)用;2013年10期

3 張勇;;數(shù)字圖像修復(fù)關(guān)鍵技術(shù)的研究與實(shí)現(xiàn)[J];安陽(yáng)師范學(xué)院學(xué)報(bào);2014年02期

4 程村;;基于蒙特卡羅方法的圖像修復(fù)快速算法[J];工程地球物理學(xué)報(bào);2006年01期

5 姜瑞;馬利莊;聶棟棟;;一種有效的大面積圖像修復(fù)方法[J];計(jì)算機(jī)應(yīng)用研究;2006年12期

6 姚曄;韋冰;;圖像修復(fù)技術(shù)研究進(jìn)展[J];企業(yè)技術(shù)開(kāi)發(fā);2007年04期

7 段漢根;汪繼文;;基于微分近似的圖像修復(fù)[J];信息技術(shù);2007年05期

8 陳芳;葉正麟;王繼紅;;基于統(tǒng)計(jì)特征的圖像修復(fù)[J];計(jì)算機(jī)工程與應(yīng)用;2007年22期

9 汪志敏;;試論數(shù)字圖像修復(fù)技術(shù)[J];張家口職業(yè)技術(shù)學(xué)院學(xué)報(bào);2007年04期

10 葛仕明;程義民;潘浩;錢(qián)振興;;基于離散優(yōu)化的圖像修復(fù)[J];中國(guó)科學(xué)技術(shù)大學(xué)學(xué)報(bào);2008年12期

相關(guān)會(huì)議論文 前10條

1 張巧煥;唐向宏;任澍;;一種基于區(qū)域搜索的快速圖像修復(fù)算法[A];浙江省電子學(xué)會(huì)2011學(xué)術(shù)年會(huì)論文集[C];2011年

2 史金鋼;齊春;;基于非局域樣本塊的圖像修復(fù)算法[A];第七屆和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會(huì)議（HHME2011)論文集【oral】[C];2011年

3 霍星;檀結(jié)慶;艾小豐;;基于隨機(jī)迭代查找的圖像修復(fù)算法[A];第六屆全國(guó)幾何設(shè)計(jì)與計(jì)算學(xué)術(shù)會(huì)議論文集[C];2013年

4 李晉江;李孟軍;范輝;;低秩近似圖像修復(fù)算法[A];第六屆全國(guó)幾何設(shè)計(jì)與計(jì)算學(xué)術(shù)會(huì)議論文集[C];2013年

5 陳延嘉;莊志軍;王美清;;一種改進(jìn)的基于樣本的圖像修補(bǔ)方法[A];全國(guó)第19屆計(jì)算機(jī)技術(shù)與應(yīng)用（CACIS）學(xué)術(shù)會(huì)議論文集（上冊(cè)）[C];2008年

6 高軍亮;徐曉剛;王建國(guó);吳晶;;一種基于圖像修復(fù)的目標(biāo)重建算法[A];2006中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];2006年

7 朱曉臨;陳曉冬;朱園珠;陳Z，

本文編號(hào)：1940818