|
|
适用于多目标图像分割的改进BVF Snake模型
|
Abstract:
参数活动轮廓模型(Snake)在计算机视觉和图像处理领域有着广泛的应用。传统的Snake算法存在许多不足，包括计算量大和当存在多目标时不能收敛到特定目标。虽然边界向量场(Boundary Vector Field, BVF) Snake减小了计算量强度，但是当存在多目标时仍然不能收敛到特定目标。本文通过力场分析，确定了BVF Snake不适用于多目标图像分割的原因；通过改进，提出一种改进的方向BVF (directional BVF, DBVF) Snake模型；在该模型中，通过在特定目标内部增加一个点，得到一个方向向量场，来确定Snake的收敛方向，使其在存在多目标时可以收敛到特定目标。本文对DBVF Snake在增大捕捉范围、添加不同噪声两个方面和常见的Snake模型进行了对比分析，同时对声呐图像进行了分割，实验结果证明了本文提出的模型(方法)对多目标图像分割的有效性。
The parametric active contour model (Snake) has a wide range of applications in the field of computer vision and image processing. The traditional Snake model has many shortcomings, including high computational effort and failure to converge to the specific target when multiple targets exist. Although the boundary vector field (BVF) Snake reduces the computational intensity, it still fails to converge to the specific target when there are multiple targets. In this paper, the force field is inspected to determine the reasons why the BVF Snake is not applicable to the segmentation of an image with multiple targets, and improvements are made to propose an improved directional BVF (DBVF) Snake model. In this model, a directional vector field is obtained by adding one point inside a specific target to determine the convergence direction of the Snake, so that it can converge to a specific target in the presence of multiple targets. In the paper, the DBVF Snake model is compared with the common Snake models in two aspects of increasing the capture range and adding different noises, and the sonar images are segmented and segmented results show that the DBVF Snake model is valid for the segmentation of an image with multiple targets.
| [1] | Jaffino, G. and Jose, J.P. (2022) Contour- and Texture-Based Analysis for Victim Identification in Forensic Odontology. Data Technologies and Applications, 56, 146-160. https://doi.org/10.1108/DTA-03-2021-0075 |
| [2] | Yang, Y., Hou. X. and Ren, H. (2021) Accurate and Efficient Image Segmentation and Bias Correction Model Based on Entropy Function and Level Sets. Information Sciences, 577, 638-662. https://doi.org/10.1016/j.ins.2021.07.069 |
| [3] | Kass, M., Witkin, A. and Terzopoulos, D. (1988) Snakes: Active Contour Models. International Journal of Computer Vision, 1, 321-331. https://doi.org/10.1007/BF00133570 |
| [4] | Li, B. and Acton, S.T. (2006) Vector Field Convolution for Image Segmentation Using Snakes. Proceedings of 2006 International Conference on Image Processing, Atlanta, 8-11 October 2006, 1637-1640.
https://doi.org/10.1109/ICIP.2006.312619 |
| [5] | Matikainen, L., Lehtomaki, M., Ahokas, E., et al. (2016) Remote Sensing Methods for Power Line Corridor Surveys. ISPRS Journal of Photogrammetry and Remote Sensing, 119, 10-31. https://doi.org/10.1016/j.isprsjprs.2016.04.011 |
| [6] | 黄征. 几何活动轮廓图像分割模型的算法研究[D]: [硕士学位论文]. 昆明: 昆明理工大学, 2022. |
| [7] | Cohen, L.D. and Cohen, I. (1993) Finite-Element Methods for Active Contour Models and Balloons for 2-D and 3-D Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15, 1131-1147.
https://doi.org/10.1109/34.244675 |
| [8] | Xu, C. and Prince, J.L. (1998) Snakes, Shapes and Gradient Vector Flow. IEEE Transactions on Image Processing, 7, 359-369. https://doi.org/10.1109/83.661186 |
| [9] | Xu, C. and Prince, J.L. (1998) Generalized Gradient Vector Flow External Forces for Active Contours. Signal Processing, 71, 131-139. https://doi.org/10.1016/S0165-1684(98)00140-6 |
| [10] | Li, C., Liu, J. and Fox, M.D. (2005) Segmentation of External Force Field for Automatic Initialization and Splitting of Snakes. Pattern Recognition, 38, 1947-1960. https://doi.org/10.1016/j.patcog.2004.12.015 |
| [11] | Li, C., Liu, J. and Fox, M.D. (2005) Segmentation of Edge Preserving Gradient Vector Flow: An Approach Toward Automatically Initializing and Splitting of Snakes. Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, 20-25 June 2005, 162-167. https://doi.org/10.1109/CVPR.2005.314 |
| [12] | Ning, J., Wu, C., Liu, S. and Yang, S. (2007) NGVF: An Improved External Force Field for Active Contour Model. Pattern Recognition Letters, 28, 58-63. https://doi.org/10.1016/j.patrec.2006.06.014 |
| [13] | Wang, Y., Liu, L., Zhang, H., et al. (2010) Image Segmentation Using Active Contours With Normally Biased GVF External Force. IEEE Signal Processing Letters, 17, 875-878. https://doi.org/10.1109/LSP.2010.2060482 |
| [14] | Qin, L., Zhu, C. and Zhao, Y., et al. (2013) Generalized Gradient Vector Flow for Snakes: New Observations, Analysis, and Improvement. IEEE Transactions on Circuits and Systems for Video Technology, 23, 883-897.
https://doi.org/10.1109/TCSVT.2013.2242554 |
| [15] | Zhu, S. and Gao, R. (2016) A Novel Generalized Gradient Vector Flow Snake Model Using Minimal Surface and Component-Normalized Method for Medical Image Segmentation. Biomedical Signal Processing and Control, 26, 1-10. https://doi.org/10.1016/j.bspc.2015.12.004 |
| [16] | 陈海燕, 张华清, 甄霞军. 一种初始轮廓位置鲁棒的混合活动轮廓模型[J]. 华中科技大学学报(自然科学版), 2021, 49(11): 53-57+63. |
| [17] | 郭宝军, 张晓冬, 崔金龙, 等. 利用改进的对称活动轮廓模型分割非匀质图像[J]. 计算机仿真, 2023, 40(1): 227-233+483. |
| [18] | Sum, K.W. and Cheung, P.Y.S. (2007) Boundary Vector Field for Parametric Active Contours. Pattern Recognition, 40, 1635-1645. https://doi.org/10.1016/j.patcog.2006.11.006 |
| [19] | Horn, B. and Schunck, B.G. (1981) Determining Optical Flow. Artificial Intelligence, 17, 185-203.
https://doi.org/10.1016/0004-3702(81)90024-2 |
| [20] | Lobregt, S. and Viergever, M.A. (1995) A Discrete Dynamic Contour Model. IEEE Transactions on Medical Imaging, 14, 12-24. https://doi.org/10.1109/42.370398 |
| [21] | Zhu, Z., Xu, X., Yang, L., et al. (2014) A Model-Based Sonar Image ATR Method Based on SIFT Features. Proceedings of Oceans 2014, Taipei, 7-10 April 2014, 1-4.
https://doi.org/10.1109/OCEANS-TAIPEI.2014.6964476 |
| [22] | 罗琴, 王艳. 无需初始轮廓的图像分割模型[J]. 计算机应用, 2021, 41(4): 1179-1183. |
| [23] | 黄涛, 李华, 周桂, 等. 实例分割方法研究综述[J]. 计算机科学与探索, 2023, 17(4): 810-825. |
