|
|
融合变分和深度先验的非均匀图像分割算法
|
Abstract:
为了尽可能精确地分割出强度不均匀图像更多的细节部分，提出一种融合深度图像先验的变分图像分割模型，利用交替方向乘子法设计相应的数值求解算法。实验结果表明，提出的模型在去噪正则化(regularization by denoising, RED)框架下融合了TV正则项捕获边缘和卷积神经网络(convolutional neural network, CNN)捕获细节的优势，尤其在处理结构丰富和纹理细致的图像时，可以分割出更多的细节，分割结果更精确。同时，提出的方法对于不同的初始轮廓具有很好的鲁棒性。此外，与对比实验中处理非均匀图像分割的方法相比，该模型算法复杂度低，具有快速高效的优势。
To segment more detailed parts of a homogeneous image as accurately as possible, a variational image segmentation model with depth image prior is proposed in this paper. The alternating direction method of multipliers (ADMM) is used to design the corresponding numerical algorithm. The results reveal that the proposed model by incorporating the denoising regularization (RED) framework with TV regularization can retain more details in images and obtain more accurate segmentation accuracy. At the same time, the model is robust to different initial contours. In addition, compared with the image segmentation method in the comparison experiment, the algorithm complexity of the proposed method is lower and has higher operational efficiency.
| [1] | 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 |
| [2] | Caselles, V., Kimmel, R. and Sapiro, G. (1997) Geodesic Active Contours. International Journal of Computer Vision, 22, 61-79. https://doi.org/10.1023/a:1007979827043 |
| [3] | Chan, T.F. and Vese, L.A. (2001) Active Contours without Edges. IEEE Transactions on Image Processing, 10, 266-277. https://doi.org/10.1109/83.902291 |
| [4] | Mumford, D. and Shah, J. (1989) Optimal Approximations by Piecewise Smooth Functions and Associated Variational Problems. Communications on Pure and Applied Mathematics, 42, 577-685. https://doi.org/10.1002/cpa.3160420503 |
| [5] | Cai, X., Chan, R., Sch？nlieb, C., Steidl, G. and Zeng, T. (2019) Linkage between Piecewise Constant Mumford-Shah Model and Rudin-Osher-Fatemi Model and Its Virtue in Image Segmentation. SIAM Journal on Scientific Computing, 41, B1310-B1340. https://doi.org/10.1137/18m1202980 |
| [6] | Ren, Y., Li, D. and Tang, L. (2023) A Variational Level Set Model Based on Additive Decomposition for Segmenting Noisy Images with Intensity Inhomogeneity. Signal Processing, 212, Article ID: 109169. https://doi.org/10.1016/j.sigpro.2023.109169 |
| [7] | Zhang, Y., Ge, Y., Guo, Y., Miao, H. and Zhang, S. (2023) An Approach for Goose Egg Recognition for Robot Picking Based on Deep Learning. British Poultry Science, 64, 343-356. https://doi.org/10.1080/00071668.2023.2171769 |
| [8] | Zosso, D., An, J., Stevick, J., Takaki, N., Weiss, M., S. Slaughter, L., et al. (2017) Image Segmentation with Dynamic Artifacts Detection and Bias Correction. Inverse Problems & Imaging, 11, 577-600. https://doi.org/10.3934/ipi.2017027 |
| [9] | Jin, Z., Wu, Y., Min, L. and Ng, M.K. (2020) A Retinex-Based Total Variation Approach for Image Segmentation and Bias Correction. Applied Mathematical Modelling, 79, 52-67. https://doi.org/10.1016/j.apm.2019.11.005 |
| [10] | Unni, V.S., Gavaskar, R.G. and Chaudhury, K.N. (2023) Compressive Sensing of ECG Signals Using Plug-and-Play Regularization. Signal Processing, 202, Article ID: 108738. https://doi.org/10.1016/j.sigpro.2022.108738 |
| [11] | Zhang, K., Li, Y., Zuo, W., Zhang, L., Van Gool, L. and Timofte, R. (2022) Plug-and-Play Image Restoration with Deep Denoiser Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 6360-6376. https://doi.org/10.1109/tpami.2021.3088914 |
| [12] | Tumanyan, N., Geyer, M., Bagon, S. and Dekel, T. (2023) Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 1921-1930. https://doi.org/10.1109/cvpr52729.2023.00191 |
| [13] | Zhu, Y., Zhang, K., Liang, J., Cao, J., Wen, B., Timofte, R., et al. (2023) Denoising Diffusion Models for Plug-and-Play Image Restoration. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, 17-24 June 2023, 1219-1229. https://doi.org/10.1109/cvprw59228.2023.00129 |
| [14] | Romano, Y., Elad, M. and Milanfar, P. (2017) The Little Engine That Could: Regularization by Denoising (Red). SIAM Journal on Imaging Sciences, 10, 1804-1844. https://doi.org/10.1137/16m1102884 |
| [15] | Zhao, Y., Liu, Q., Tian, H., Ling, B.W. and Zhang, Z. (2024) Deepred Based Sparse SAR Imaging. Remote Sensing, 16, Article No. 212. https://doi.org/10.3390/rs16020212 |
| [16] | Peng, J., Xu, Y., Luo, L., Liu, H., Lu, K. and Liu, J. (2023) Regularized Denoising Masked Visual Pretraining for Robust Embodied Pointgoal Navigation. Sensors, 23, Article No. 3553. https://doi.org/10.3390/s23073553 |
| [17] | Mataev, G., Milanfar, P. and Elad, M. (2019) DeepRED: Deep Image Prior Powered by RED. Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops, Seoul, 27-28 October 2019. https://openaccess.thecvf.com/content_ICCVW_2019/papers/LCI/Mataev_DeepRED_Deep_Image_Prior_Powered_by_RED_ICCVW_2019_paper.pdf |
| [18] | Iskender, B., Klasky, M.L. and Bresler, Y. (2023) RED-PSM: Regularization by Denoising of Partially Separable Models for Dynamic Imaging. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), Paris, 1-6 October 2023, 10561-10570. https://doi.org/10.1109/iccv51070.2023.00972 |
| [19] | Iskender, B., Klasky, M.L. and Bresler, Y. (2023). Dynamic Tomography Reconstruction via Low-Rank Modeling with a RED Spatial Prior. 2023 IEEE 9th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Herradura, 10-13 December 2023, 506-510. https://doi.org/10.1109/camsap58249.2023.10403435 |
| [20] | Zhu, W., Qiu, P., Dumitrascu, O.M., Sobczak, J.M., Farazi, M., Yang, Z., et al. (2023) OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing. In: Frangi, A., et al., Information Processing in Medical Imaging, Springer, 415-427. https://doi.org/10.1007/978-3-031-34048-2_32 |
| [21] | Land, E.H. (1977) The Retinex Theory of Color Vision. Scientific American, 237, 108-128. https://doi.org/10.1038/scientificamerican1277-108 |
| [22] | Hussein, R.R., Hamodi, Y.I. and Sabri, R.A. (2019) Retinex Theory for Color Image Enhancement: A Systematic Review. International Journal of Electrical and Computer Engineering (IJECE), 9, 5560-5569. https://doi.org/10.11591/ijece.v9i6.pp5560-5569 |
| [23] | Zhang, K., Zuo, W. and Zhang, L. (2018) FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising. IEEE Transactions on Image Processing, 27, 4608-4622. https://doi.org/10.1109/tip.2018.2839891 |
| [24] | Yashtini, M. (2022) Convergence and Rate Analysis of a Proximal Linearized ADMM for Nonconvex Nonsmooth Optimization. Journal of Global Optimization, 84, 913-939. https://doi.org/10.1007/s10898-022-01174-8 |
| [25] | Gong, Y., Li, Y. and Freris, N.M. (2022) FedADMM: A Robust Federated Deep Learning Framework with Adaptivity to System Heterogeneity. 2022 IEEE 38th International Conference on Data Engineering (ICDE), Kuala Lumpur, 9-12 May 2022, 2575-2587. https://doi.org/10.1109/icde53745.2022.00238 |
| [26] | Zhao, X., Pang, Y., Zhang, L., Lu, H. and Zhang, L. (2020) Suppress and Balance: A Simple Gated Network for Salient Object Detection. In: Computer Vision—ECCV 2020, Springer, 35-51. https://doi.org/10.1007/978-3-030-58536-5_3 |
| [27] | Qin, X., Fan, D.P., Huang, C., et al. (2021) Boundary-Aware Segmentation Network for Mobile and Web Applications. https://arxiv.org/pdf/2101.04704 |
| [28] | Bui, K., Lou, Y., Park, F. and Xin, J. (2023) Difference of Anisotropic and Isotropic TV for Segmentation under Blur and Poisson Noise. Frontiers in Computer Science, 5, Article ID: 1131317. https://doi.org/10.3389/fcomp.2023.1131317 |
| [29] | Vaassen, F., Hazelaar, C., Vaniqui, A., Gooding, M., van der Heyden, B., Canters, R., et al. (2020) Evaluation of Measures for Assessing Time-Saving of Automatic Organ-at-Risk Segmentation in Radiotherapy. Physics and Imaging in Radiation Oncology, 13, 1-6. https://doi.org/10.1016/j.phro.2019.12.001 |
| [30] | Liu, Q., Peng, H., Chen, J. and Gao, H. (2021) RETRACTED: Design and Implementation of Parallel Algorithm for Image Matching Based on Hausdorff Distance. Microprocessors and Microsystems, 82, Article ID: 103919. https://doi.org/10.1016/j.micpro.2021.103919 |
| [31] | Min, L., Cui, Q., Jin, Z. and Zeng, T. (2021) Inhomogeneous Image Segmentation Based on Local Constant and Global Smoothness Priors. Digital Signal Processing, 111, Article ID: 102989. https://doi.org/10.1016/j.dsp.2021.102989 |
