An Alpha Matting Algorithm Based on Micro-scale Searching for High-Resolution Images
FENG Fujian1,2, YANG Yuan1,2, TAN Mian1,2, GOU Hongshan1,2, LIANG Yihui3, WANG Lin1,2
1. College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang 550025; 2. Key Laboratory of Pattern Recognition and Intelligent Systems of Guizhou Province, Guizhou Minzu University, Guiyang 550025; 3. School of Computer Engineering, University of Electronic Science and Technology of China, Zhongshan Institute, Zhongshan 528400
Abstract：High-resolution image matting is essentially a large-scale combinatorial optimization for foreground/background pixel pairs. However, there is few research achievements on this issue. Alpha matte inverse extraction occurs when the foreground and the background in an image are highly similar. To address this problem, a decision set decomposition strategy is designed to effectively decompose high-resolution image matting problems. Moreover, a optimized information transmission strategy is designed, the weight relationship between sub-problems is obtained, and the optimization sequence of the image matting problem is established. Based on the optimized information transmission strategy, an alpha matting algorithm based on micro-scale searching(MS-AM) is proposed. MS-AM effectively solves the issue of alpha matte inverse extraction in high-resolution image matting problems by searching through effective decision subsets instead of the entire decision set, providing insights for the analysis of large-scale combinatorial optimization problems. The alphamatting benchmark dataset is selected as testing data, and MS-AM is compared with typical matting optimization algorithms. Results demonstrate that MS-AM can address alpha matte inverse extraction problem when the foreground is similar to the background and improve the alpha matting accuracy with significantly reduced dimension of high-resolution image matting problem.
[1] LIN S C, YANG L J, SALEEMI I, et al. Robust High-Resolution Video Matting with Temporal Guidance//Proc of the IEEE/CVF Winter Conference on Applications of Computer Vision. Washington, USA: IEEE, 2022: 238-247. [2] DING H H, ZHANG H, LIU C, et al. Deep Interactive Image Ma-tting with Feature Propagation. IEEE Transactions on Image Processing, 2022, 31: 2421-2432. [3] GONG M L, QIAN Y M, CHENG L.Integrated Foreground Segmentation and Boundary Matting for Live Videos. IEEE Transactions on Image Processing, 2015, 24(4): 1356-1370. [4] SUN Y N, TANG C K, TAI Y W. Semantic Image Matting//Proc of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2021: 11115-11124. [5] PORTER T, DUFF T. Compositing Digital Images. ACM SIGGRAPH Computer Graphics, 1984, 18(3): 253-259. [6] RHEMANN C, ROTHER C, WANG J, et al. A Perceptually Motivated Online Benchmark for Image Matting//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2009: 1826-1833. [7] 梁椅辉,黄翰,蔡昭权,等.自然图像抠图技术综述.计算机应用研究, 2021, 38(5): 1294-1301. (LIANG Y H, HUANG H, CAI Z Q, et al. Survey of Natural Image Matting. Application Research of Computers, 2021, 38(5): 1294-1301.) [8] LI X Q, LI J D, LU H.A Survey on Natural Image Matting with Closed-Form Solutions. IEEE Access, 2019, 7: 136658-136675. [9] AKSOY Y, AYDIN T O, POLLEFEYS M. Designing Effective Inter-Pixel Information Flow for Natural Image Matting//Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 29-37. [10] LIANG Y H. GOU H S, FENG F J, et al. Natural Image Matting Based on Surrogate Model. Applied Soft Computing, 2023. DOI: 10.1016/j.asoc.2023.110407. [11] HUANG H, LIANG Y H, YANG X W, et al. Pixel-Level Discrete Multiobjective Sampling for Image Matting. IEEE Transactions on Image Processing, 2019, 28(8): 3739-3751. [12] CAO G Y, LI J W, CHEN X W, et al. Patch-Based Self-Adaptive Matting for High-Resolution Image and Video. The Visual Compu-ter, 2019, 35(1): 133-147. [13] ZHU X Y, WANG P, HUANG Z H. Adaptive Propagation Matting Based on Transparency of Image. Multimedia Tools and Applications, 2018, 77(15): 19089-19112. [14] WENG T H, LI K C, YANG Z L, et al. On the Code Modernization of Shared Sampling Alpha Matting with OpenMP. Future Generation Computer Systems, 2020, 107: 177-191. [15] TANG J W, AKSOY Y, OZTIRELI C, et al. Learning-Based Sampling for Natural Image Matting//Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 3055-3063. [16] FENG F J, HUANG H, LIU D, et al. Local Complexity Difference Matting Based on Weight Map and Alpha Mattes. Multimedia Tools and Applications, 2022, 81: 43357-43372. [17] LIANG Y H, HUANG H, CAI Z Q.PSO-ACSC: A Large-Scale Evolutionary Algorithm for Image Matting. Frontiers in Computer Science, 2020, 14(6). DOI: 10.1007/s11704-019-8441-5. [18] LIANG Y H, FENG F J, CAI Z Q.Pyramid Matting: A Resource-Adaptive Multi-scale Pixel Pair Optimization Framework for Image Matting. IEEE Access, 2020, 8: 93487-93498. [19] MOHAPATRA P, DAS K N, ROY S. Novel Competitive Swarm Optimizer for Sampling-Based Image Matting Problem//ELÇI A, SA P K, MODI C N, et al., eds. Smart Computing Paradigms: New Progresses and Challenges. Berlin, Germany: Springer, 2020: 109-120. [20] LIANG Y H, HUANG H, CAI Z Q, et al. Multiobjective Evolutionary Optimization Based on Fuzzy Multicriteria Evaluation and Decomposition for Image Matting. IEEE Transactions on Fuzzy Systems, 2019, 27(5): 1100-1111. [21] WANG X F, LI S J, SUI L S, et al. Quick Automatic Head Image Matting Method Based on Segmentation and Propagation. Pattern Recognition Letters, 2020, 130: 30-37. [22] 冯夫健,黄翰,吴秋霞,等.基于群体协同优化的高清图像前景遮罩提取算法.中国科学(信息科学), 2020, 50(3): 424-437. (FENG F J, HUANG H, WU Q X, et al. An Alpha Matting Algorithm Based on Collaborative Swarm Optimization for High-Resolution Images. Chinese Science(Information Science), 2020, 50(3): 424-437.) [23] HUANG H, FENG F J, HUANG S Q, et al. Microscale Sear-ching Algorithm for Coupling Matrix Optimization of Automated Microwave Filter Tuning. IEEE Transactions on Cybernetics, 2023, 53(5): 2829-2840. [24] KUMAH C, ZHANG N, RAJI R K, et al. Unsupervised Segmentation of Printed Fabric Patterns Based on Mean Shift Algorithm. The Journal of the Textile Institute, 2022, 113(1). DOI: 10.1080/00405000.2020.1867413. [25] COMANICIU D, MEER P.Mean Shift: A Robust Approach Toward Feature Space Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619. [26] RYOYA Y, TOSHIYUKI T.Properties of Mean Shift. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(9): 2273-2286. [27] 冯夫健,黄翰,张宇山,等.基于等同关系模型的演化算法期望首达时间对比分析.计算机学报, 2019, 42(10): 2297-2308. (FENG F J, HUANG H, ZHANG Y S, et al. Comparative Analysis for First Hitting Time of Evolutionary Algorithms Based on Equal-in-Time Model. Chinese Journal of Computers, 2019, 42(10): 2297-2308.) [28] EBERHART R, KENNEDY J. A New Optimizer Using Particle Swarm Theory//Proc of the 6th International Symposium on Micro Machine and Human Science. Washington, USA: IEEE, 1995: 39-43. [29] SONG X F, ZHANG Y, GUO Y N, et al. Variable-Size Cooperative Coevolutionary Particle Swarm Optimization for Feature Selection on High-Dimensional Data. IEEE Transactions on Evolutionary Computation, 2020, 24(5): 882-895. [30] CAI I Q, LÜ L, HUANG H, et al. Improving Sampling-Based Image Matting with Cooperative Coevolution Differential Evolution Algorithm. Soft Computing, 2017, 21: 4417-4430. [31] FENG F J, HUANG H, LIANG Y H. Graph-Order Optimization Algorithm Based on Equal-in-Space Distance Model for High-Resolution Image Matting//Proc of the IEEE 7th International Confe-rence on Cloud Computing and Intelligent Systems. Washington, USA: IEEE, 2021: 122-127.
2023, Vol. 36 
