發(fā)布時(shí)間：2018-03-05 22:09

  本文選題：圖像配準(zhǔn)　切入點(diǎn)：非剛性配準(zhǔn)　出處：《光學(xué)精密工程》2017年09期 　論文類(lèi)型：期刊論文

【摘要】：考慮傳統(tǒng)非剛性圖像配準(zhǔn)方法無(wú)法同時(shí)滿(mǎn)足配準(zhǔn)精度和配準(zhǔn)時(shí)間要求,綜合圖像的特征和灰度信息,提出了幾種改進(jìn)的非剛性圖像配準(zhǔn)方法:基于圓形描述子特征的非剛性配準(zhǔn)方法(Circle Descriptor Feature,CDF),基于動(dòng)態(tài)驅(qū)動(dòng)力Demons的非剛性配準(zhǔn)方法(Dynamic Driving Force Demons,DDFD),和基于圖像特征和光流場(chǎng)的非剛性配準(zhǔn)方法。CDF方法通過(guò)提取圖像的特征點(diǎn),采用圓形描述子代替?zhèn)鹘y(tǒng)方法的正方形描述子來(lái)保證圖像的旋轉(zhuǎn)不變性,提高配準(zhǔn)速度;DDFD方法通過(guò)引入驅(qū)動(dòng)力系數(shù)動(dòng)態(tài)改變驅(qū)動(dòng)力,有效地解決了傳統(tǒng)方法配準(zhǔn)時(shí)間和配準(zhǔn)精度低的問(wèn)題;基于圖像特征和光流場(chǎng)的非剛性配準(zhǔn)方法則首先提取浮動(dòng)圖像和參考圖像的特征點(diǎn),然后利用提取的特征點(diǎn)進(jìn)行粗配準(zhǔn)(特征級(jí)配準(zhǔn)),再采用基于光流場(chǎng)的方法進(jìn)行精細(xì)配準(zhǔn)(像素級(jí)配準(zhǔn)),最終實(shí)現(xiàn)配準(zhǔn)精度和配準(zhǔn)時(shí)間的兼顧。對(duì)checkboard測(cè)試圖像、自然圖像、腦部MR圖像、肝部CT圖像進(jìn)行了實(shí)驗(yàn)測(cè)試,結(jié)果表明,本文方法在配準(zhǔn)時(shí)間、配準(zhǔn)精度及對(duì)大形變圖像的適應(yīng)性方面均優(yōu)于傳統(tǒng)尺度不變特征轉(zhuǎn)換(SIFT)、加速魯棒特征(SURF)、Demons、Active Demons和全變差正則項(xiàng)-L~1范數(shù)項(xiàng)(TV-L~1)等方法。
[Abstract]:Considering that the traditional non-rigid image registration method can not meet the registration accuracy and registration time requirements at the same time, the image features and gray level information are synthesized. Several improved non-rigid image registration methods are proposed: circle Descriptor feature based non-rigid registration method based on circular descriptor feature, dynamic Driving Force Demonsd FDF based on dynamic driving force Demons, and image feature and optical flow field. The non-rigid registration method. CDF method extracts the feature points of the image. The circular descriptor is used to replace the square descriptor of the traditional method to ensure the rotation invariance of the image, and the dynamic driving force is changed by introducing the driving force coefficient to improve the registration speed. It effectively solves the problems of low registration time and registration accuracy in traditional methods, and the non-rigid registration method based on image feature and optical flow field firstly extracts the feature points of floating image and reference image. Then the extracted feature points are used for rough registration (feature gradation), and then fine registration (pixel gradation) based on optical flow field is used to achieve both registration accuracy and registration time. Mr images of brain and CT images of liver were tested experimentally. The results showed that the registration time of this method, The registration accuracy and adaptability to large deformation images are better than those of the traditional scale invariant feature conversion (SIFT), and the methods of accelerating robust features such as robust Demons and TV-L ~ (1)) are also discussed in this paper, and the results are as follows: (1) the accuracy of registration and the adaptability to large deformation images are better than those of the traditional scale-invariant feature conversion (SIFT).
【作者單位】： 山東大學(xué)(威海)機(jī)電與信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(No.81671848,No.81371635) 山東省重點(diǎn)研發(fā)計(jì)劃資助項(xiàng)目(No:2016GGX101017)
【分類(lèi)號(hào)】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王艷陽(yáng);傅小龍;夏冰;吳正琴;樊e，

本文編號(hào)：1572096