Frontiers in Physics ( IF 3.1 ) Pub Date : 2021-09-16 , DOI: 10.3389/fphy.2021.742296 Zhentao Pang , Hang Zhang , Yu Wang , Letian Zhang , Yingchun Wu , Xuecheng Wu
Accurate particle detection is a common challenge in particle field characterization with digital holography, especially for gel secondary breakup with dense complex particles and filaments of multi-scale and strong background noises. This study proposes a deep learning method called Mo-U-net which is adapted from the combination of U-net and Mobilenetv2, and demostrates its application to segment the dense filament-droplet field of gel drop. Specially, a pruning method is applied on the Mo-U-net, which cuts off about two-thirds of its deep layers to save its training time while remaining a high segmentation accuracy. The performances of the segmentation are quantitatively evaluated by three indices, the positive intersection over union (PIOU), the average square symmetric boundary distance (ASBD) and the diameter-based prediction statistics (DBPS). The experimental results show that the area prediction accuracy (PIOU) of Mo-U-net reaches 83.3
中文翻译:
使用 Mo-U-Net 识别数字全息中的多尺度致密凝胶细丝-液滴场
精确的粒子检测是数字全息技术粒子场表征中的一个常见挑战,特别是对于具有密集复杂粒子和多尺度和强背景噪声的细丝的凝胶二次破碎。本研究提出了一种名为 Mo-U-net 的深度学习方法,该方法由 U-net 和 Mobilenetv2 组合而成,并演示了其在凝胶滴的密集细丝-液滴场分割中的应用。特别是,在 Mo-U-net 上应用了一种剪枝方法,它剪掉了大约三分之二的深层,以节省训练时间,同时保持较高的分割精度。分割的性能通过三个指标进行定量评估,正交叉联合(PIOU),均方对称边界距离 (ASBD) 和基于直径的预测统计 (DBPS)。实验结果表明,Mo-U-net的面积预测精度(PIOU)达到83.3