首都医科大学生物医学工程学院(北京 100069)
胡帆,博士,副教授。E-mail:hufan@ccmu.edu.cn
收稿:2025-07-18,
修回:2025-09-09,
纸质出版:2026-04-20
移动端阅览
张以诺,张家耀,胡帆.基于图像处理的颗粒参数测量方法研究进展[J].北京生物医学工程,2026,45(2):201-206.
ZHANG Yinuo,ZHANG Jiayao,HU Fan.Research progress in measuring particle parameters based on image processing methods[J].Beijing Biomedical Engineering,2026,45(2):201-206.
张以诺,张家耀,胡帆.基于图像处理的颗粒参数测量方法研究进展[J].北京生物医学工程,2026,45(2):201-206. DOI: 10.3969/j.issn.1002-3208.2026.02.013.
ZHANG Yinuo,ZHANG Jiayao,HU Fan.Research progress in measuring particle parameters based on image processing methods[J].Beijing Biomedical Engineering,2026,45(2):201-206. DOI: 10.3969/j.issn.1002-3208.2026.02.013.
颗粒材料在医药、材料科学等多领域作用关键。在颗粒学研究中,颗粒形态信息检测与评估是关键问题,传统手工计算方法因主观性和低效率,无法满足现代科研和工业生产需求。计算机图像处理技术优势显著,为颗粒图像参数自动提取提供有效手段。本文梳理文献,归纳颗粒图像处理算法及进展。预处理方面,涉及颗粒图像滤波算法评估和前沿深度学习去噪模型应用。分割环节,总结分水岭算法解决分割问题的方案、适配颗粒图像的水平集算法、凹点检测技术进展及基于霍夫变换和随机圆检测的成果,关注颗粒粘连和堆叠时的分割策略。此外,回顾深度学习在该领域的成果,分析U-Net与Mask R-CNN模型优势及改进,探讨注意力机制等改进方法成果。最后提出未来颗粒图像参数测量的三大趋势:高性能定制化算法、通用型算法和深度学习融合算法。
Particle materials are of critical importance across various disciplines, including medicine and materials science. In the field of particle science research, the accurate detection and evaluation of particle morphology are essential tasks. Traditional manual methods, however, are inherently subjective and inefficient, thus failing to meet the demands of modern scientific research and industrial applications. Computer image processing technologies offer significant advantages and provide an effective solution for the automated extraction of particle image parameters. This paper presents a comprehensive review of existing literature, summarizing the algorithms and advancements in particle image processing. In the area of image preprocessing, it discusses the performance of particle image filtering algorithms and the application of cutting-edge deep learning-based denoising models. Regarding image segmentation, the paper outlines how the watershed algorithm addresses segmentation challenges, explores the level set method tailored for particle images, reviews progress in concave point detection techniques, and highlights achievements based on Hough transform and random circle detection. Particular attention is given to segmentation strategies for scenarios involving adhered or stacked particles. Furthermore, the paper reviews recent advances in deep learning, analyzes the strengths and enhancements of architectures such as U-Net and Mask R-CNN, and discusses improvements that inegrate attention mechanisms. Finally, three major future directions in particle image parameter measurement are proposed: high-performance customized algorithms, general-purpose algorithms and deep learning fusion algorithms.
申冉, 甄彤, 李智慧,等. 谷类作物粘连颗粒图像分割方法研究进展[J]. 中国粮油学报, 2022, 37(10): 313-320.
Shen R, Zhen T, Li ZH, et al. Research progress in image segmentation methods of cereal adhesion grains[J]. Journal of the Chinese Cereals and Oils Association, 2022, 37(10): 313-320.
司秀娟,王红强,宋良图. 基于图像处理的菌落自动计数系统[J]. 北京生物医学工程, 2017, 36(6): 633-638.
Si XJ, Wang HQ, Song LT. Automatic colony counting system based on image processing[J]. Beijing Biomedical Engineering, 2017, 36(6): 633-638.
高鹏, 石晓龙. 基于透射电子显微镜的纳米颗粒图像识别研究综述[J]. 广州大学学报(自然科学版), 2019, 18(1): 73-78.
Gao P, Shi XL. Review of nanoparticles image recognition in TEM micrographs[J]. Journal of Guangzhou University: Natural Science Edition, 2019, 18(1): 73-78.
Tawfik MS, Adishesha AS, Hsi Y, et al. Comparative study of traditional and deep-learning denoising approaches for image-based petrophysical characterization of porous media[J]. Frontiers in Water, 2022, 3: 800369.
郭观凯, 刘伟, 余玲玲, 等. 基于改进FAST与分水岭算法的颗粒图像分割[J]. 中国粉体技术, 2019, 25(2): 61-67.
Guo GK, Liu W, Yu LL, et al. Image segmentation of touching particles based on improved FAST and watershed algorithm[J]. China Powder Science and Technology, 2019, 25(2): 61-67.
王增硕, 刘溢文, 关子昂,等. 基于自适应多重欧氏距离变换的分水岭粘连颗粒分割方法[J]. 电脑知识与技术, 2022, 18(3): 93-96.
Osher S, Fedkiw R, Piechor K. Level set methods and dynamic implicit surfaces[J]. Applied Mechanics Reviews, 2004, 57(3): B15.
Chan TF, Vese LA. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2): 266-277.
Li C, Xu C, Gui C, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions on Image Processing, 2010, 19(12): 3243-3254.
Li C, Kao CY, Gore JC, et al. Minimization of region-scalable fitting energy for image segmentation[J]. IEEE Transactions on Image Processing, 2008, 17(10): 1940-1949.
陈颖. 基于偏微分方程的纳米颗粒尺寸测量方法研究[D]. 天津: 天津工业大学, 2016.
Wang T, Fei W, Ehinger KA, et al. Improved level set method for particle reconstruction from X-ray computed tomography images[J]. Powder Technology, 2025, 455: 120743.
樊蒙蒙. 基于PCNN和凹点的粘连大米图像分割[D]. 郑州: 河南工业大学, 2019.
Fan MM. Image segmentation of adhesive rice based on PCNN and pit[D]. Zhengzhou: Henan University of Technology, 2019.
孙卫红, 洪徐健, 梁曼, 等. 基于凹点定向腐蚀的粘连蚕茧图像分割方法[J]. 蚕业科学, 2019, 45(3): 369-376.
Sun WH, Hong XJ, Liang M, et al. Image segmentation method for adhesive cocoons based on directional erosion in concave point[J]. Science of Sericulture, 2019, 45(3): 369-376.
曾凡智, 黄子豪, 周燕,等. 基于改进分水岭-凹点分割的矿石粒径分级检测方法[J]. 计算机测量与控制, 2023, 31(8): 31-37.
Zeng FZ, Huang ZH, Zhou Y, et al. Ore particle size classification detection method based on improved watershed-concave point segmentation[J]. Computer Measurement Control, 2023, 31(8): 31-37.
Chen TC, Chung KL. An efficient randomized algorithm for detecting circles[J]. Computer Vision and Image Understanding, 2001, 83(2): 172-191.
Alomari YM, Abdullah SNHS, Azma RZ, et al. Automatic detection and quantification of WBCs and RBCs using iterative structured circle detection algorithm[J]. Computational and Mathematical Methods in Medicine, 2014, 2014: 979302.
秦长泽. 球团颗粒粒度检测系统的研究[D]. 武汉: 武汉科技大学, 2015.
Qin CZ. A dissertation submitted in partial fulfillment of the requirements for the degree of master in engineering[D]. Wuhan: Wuhan University of Science and Technology, 2015.
牛利, 尹唱唱, 刘喜禄,等. 一种基于迭代直径圆检测的大气颗粒物图像分割方法[J]. 中国科技论文, 2018, 13(20): 2330-2336.
Niu L, Yin CC, Liu XL, et al. An image segmentation method of atmospheric particulates based on iterative diameter circle detection[J]. China Sciencepaper, 2018, 13(20): 2330-2336.
张晗, 廖福元. 一种基于显微图像的细胞计数技术研究[J]. 国外电子测量技术, 2021, 40(10): 123-126.
Zhang H, Liao FY. Research on cell counting technology based on microscopic image[J]. Foreign Electronic Measurement Technology, 2021, 40(10): 123-126.
陈建湟, 张中俭, 徐文杰,等. 基于数字图像处理的矿物颗粒形态定量分析[J]. 工程地质学报, 2021, 29(1): 59-68.
Chen JH, Zhang ZJ, Xu WJ, et al. Quantitative method of shape parameters of mineral particles based on image processing[J]. Journal of Engineering Geology, 2021, 29(1): 59-68.
吴秀君. 基于BP的食品外观品质检测可视化系统研究[J]. 粮食与饲料工业, 2023(6): 65-69.
Wu XJ. Research on visual system of food appearance quality detection based on BP[J]. Cereal Feed Industry, 2023(6): 65-69.
Zhou Z, Siddiquee MMR, Tajbakhsh N, et al. UNet++: a nested U-Net architecture for medical image segmentation[J]. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support,2018, 11045: 3-11.
荣亚琪. 基于常微分方程和标记分水岭算法的细胞图像分割[D]. 长春: 长春工业大学, 2022.
Rong YQ. Cell image segmentation based on neural ordinary differential equation and marker watershed algorithm[D]. Changchun: Changchun University of Technology, 2022.
Cao H, Wang Y, Chen J, et al. Swin-Unet: Unet-like pure transformer for medical image segmentation[C]// Computer Vision-ECCV 2022 Workshops. Tel Aviv, Israel: Springer Cham, 2023: 205-218.
王孝鹤. 基于Transformer网络架构的催化剂纳米颗粒识别与分割[D]. 大连: 大连交通大学, 2023.
Wang XH. Recognition and segmentation of catalyst nanoparticles based on Transformer network architecture[D]. Dalian: Dalian Jiaotong University, 2023.
李颖, 李秀宇, 卢兆林, 等. 基于深度学习的煤粉颗粒CT图像分割方法[J]. 计算机工程与设计, 2022, 43(8): 2252-2259.
Li Y, Li XY, Lu ZL, et al. Coal particle CT image segmentation method based on deep learning[J]. Computer Engineering and Design, 2022, 43(8): 2252-2259.
陈宗元,张磊磊,赵宁宁,等. 混合颗粒系重叠图像分割与分类方法研究[J]. 计量学报, 2022, 43(6): 746-753.
Chen ZY, Zhang LL, Zhao NN, et al. Research on segmentation and classification methods of mixed overlapped particle images[J]. Acta Metrologica Sinica, 2022, 43(6): 746-753.
Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas, NV, USA: IEEE Press, 2016: 779-788.
Sapkota R, Flores-Calero M, Qureshi R, et al. YOLO advances to its genesis: a decadal and comprehensive review of the You Only Look Once (YOLO) series[J]. Artificial Intelligence Review, 2025, 58: 274.
肖成勇, 李擎, 王莉, 等. 基于CBAM-Unet的铁矿球团边缘分割实验方法[J]. 烧结球团, 2022, 47(2): 8-15, 23.
Xiao CY, Li Q, Wang L, et al. Edge segmentation experimental method of iron ore pellets based on CBAM-Unet[J]. Sintering and Pelletizing, 2022, 47(2): 8-15, 23.
吴雪丽, 齐苏敏, 孟静, 等. MSE-UNet: 基于多尺度特征和注意力机制的细胞分割模型[J]. 曲阜师范大学学报(自然科学版), 2023, 49(2): 71-76.
Wu XL, Qi SM, Meng J, et al. MSE-UNet: cell segmentation model based on multiscale features and attention mechanisms[J]. Journal of Qufu Normal University (Natural Science), 2023, 49(2): 71-76.
贝琛圆, 于海滨, 潘勉, 等. 基于改进U-Net网络的腺体细胞图像分割算法[J]. 电子科技, 2019, 32(11): 18-22.
Bei CY, Yu HB, Pan M, et al. Gland cell image segmentation algorithm based on improved U-Net network[J]. Electronic Science and Technology, 2019, 32(11): 18-22.
周涛. 基于改进U-net网络的腺体细胞图像分割算法应用研究[J]. 现代信息科技, 2022, 6(13): 94-97.
Zhou T. Application research of glandular cell image segmentation algorithm based on improved U-net network[J]. Modern Information Technology, 2022, 6(13): 94-97.
杨智宏, 贺石中, 冯伟, 等. 基于Mask R-CNN网络的磨损颗粒智能识别与应用[J]. 摩擦学学报, 2021, 41(1): 105-114.
Yang ZH, He SZ, Feng W, et al. Intelligent identification of wear particles based on Mask R-CNN network and application[J]. Tribology, 2021, 41(1): 105-114.
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621