基于鄰域結(jié)構(gòu)和高斯混合模型的非剛性點(diǎn)集配準(zhǔn)算法
doi: 10.11999/JEIT150501
-
2.
(同濟(jì)大學(xué)電子與信息工程學(xué)院 上海 201804) ②(泰山醫(yī)學(xué)院信息工程學(xué)院 泰安 271016)
基金項(xiàng)目:
山東省自然科學(xué)基金(ZR2015FL005)，泰安市科技發(fā)展計(jì)劃(2015GX2016)
Non-rigid Point Set Registration Based on Neighbor Structure and Gaussian Mixture Models
-
2.
(College of Electronic Information and Engineering, Tongji University, Shanghai 201804, China)
Funds:
Shandong Provincial Natural Science Foundation, China (ZR2015FL005), Taian Science and Technology Development Program, China (2015GX2016)
-
摘要: 非剛性點(diǎn)集配準(zhǔn)算法在實(shí)際應(yīng)用中要求對噪聲、遮擋或異常點(diǎn)具有很好的魯棒性。該文采用高斯混合模型并結(jié)合點(diǎn)的鄰域結(jié)構(gòu)信息實(shí)現(xiàn)非剛性點(diǎn)集配準(zhǔn)。使用高斯混合模型表示模型點(diǎn)集，通過高斯徑向基函數(shù)構(gòu)建變換模型。并根據(jù)點(diǎn)的鄰域結(jié)構(gòu)信息決定高斯混合模型中每個(gè)高斯組成部分所占的比例。在EM算法的期望步(E-step)階段求解點(diǎn)的對應(yīng)關(guān)系，在最大化步(M-step)階段求解異常點(diǎn)比例系數(shù)和變換的閉合形式解，直至算法收斂得到最優(yōu)解。通過在合成數(shù)據(jù)和實(shí)際的視網(wǎng)膜圖像上的實(shí)驗(yàn)，與目前幾種先進(jìn)的點(diǎn)集配準(zhǔn)方法進(jìn)行了比較，證明該算法具有較好的配準(zhǔn)效果和魯棒性。
-
關(guān)鍵詞:
- 圖像配準(zhǔn) /
- 非剛性點(diǎn)集配準(zhǔn) /
- 高斯混合模型 /
- 結(jié)構(gòu)描述符
Abstract: In the practical application, non-rigid point set registration should be robust for noise, occlusion or outliers. In this paper, Gaussian Mixture Model (GMM) and neighborhood structure information are used for the non-rigid point set registration. Gaussian Mixture Model is used to represent the model set, and the transformation is built by using Gaussian radial basis function. The proportion of each Gaussian component is decided by the neighborhood structure information of points. In E-step of the EM algorithm the correspondence is solved, and in M-step the outlier ratio and the closed-form solution of the transformation are calculated. Until convergence the optimal solution is obtained. As compared to the state-of-the-art algorithms, the experiments with synthetic data and real data of the retina images show that the proposed method can improve the robustness and the accuracy. -
BESL P J and MCKAY N D. Method for registration of 3-D shapes[C]. Robotics-DL tentative. International Society for Optics and Photonics, Boston, 1992: 586-606. CHUI H and RANGARAJAN A. A new point matching algorithm for non-rigid registration[J]. Computer Vision and Image Understanding, 2003, 89(2): 114-141. BELONGIE S, MALIK J, and PUZICHA J. Shape matching and object recognition using shape contexts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(4): 509-522. MA J, ZHAO J, TIAN J, et al. Robust estimation of nonrigid transformation for point set registration[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, 2013: 2147-2154. CHEN J, MA J, YANG C, et al. Non-rigid point set registration via coherent spatial mapping[J]. Signal Processing, 2015, 106: 62-72. ZHENG Y and DOERMANN D. Robust point matching for nonrigid shapes by preserving local neighborhood structures [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 643-649. GE S, FAN G, and DING M. Non-rigid point set registration with global-local topology preservation[C]. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Columbus, 2014: 245-251. TANG J, SHAO L, and ZHEN X. Robust point pattern matching based on spectral context[J]. Pattern Recognition, 2014, 47(3): 1469-1484. LEE J H and WON C H. Topology preserving relaxation labeling for nonrigid point matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(2): 427-432. YAN X, WANG W, ZHAO J, et al. Relaxation labeling for non-rigid point matching under neighbor preserving[J]. Journal of Central South University, 2013, 20: 3077-3084. ZHAO H, JIANG B, TANG J, et al. Image matching using a local distribution based outlier detection technique[J]. Neurocomputing, 2015, 148: 611-618. 秦紅星, 徐雷. 基于信息論的 KL-Reg 點(diǎn)云配準(zhǔn)算法[J]. 電子與信息學(xué)報(bào), 2015, 37(6): 1520-1524. doi: 10.11999/ JEIT141248. QIN Hongxing and XU Lei. Information theory based KL-Reg point cloud registration[J]. Journal of Electronics Information Technology, 2015, 37(6): 1520-1524. doi: 10. 11999/JEIT141248. TAO W and SUN K. Asymmetrical gauss mixture models for point sets matching[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, 2014: 1598-1605. ZHOU Z, ZHENG J, DAI Y, et al. Robust non-rigid point set registration using studentst mixture model[J]. PlosOne, 2014, 9(3): e91381. JIAN B and VEMURI B C. Robust point set registration using gaussian mixture models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1633-1645. MYRONENKO A and SONG X. Point set registration: coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2262-2275. ZHAO J, MA J, TIAN J, et al. A robust method for vector field learning with application to mismatch removing[C]. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, 2011: 2977-2984. 趙燁, 蔣建國, 洪日昌. 基于空間約束的快速魯棒特征匹配優(yōu)化[J]. 電子與信息學(xué)報(bào), 2014, 36(11): 2571-2577. doi: 10.3724/ SP.J.1146.2013.01960. ZHAO Ye, JIANG Jianguo, and HONG Richang. A speeded up robust feature matching optimization based on apatial constraint[J]. Journal of Electronics Information Technology, 2014, 36(11): 2571-2577. doi: 10.3724/ SP.J. 1146.2013.01960. -
計(jì)量
- 文章訪問數(shù): 1891
- HTML全文瀏覽量: 267
- PDF下載量: 748
- 被引次數(shù): 0
下載:
