Journal of Applied Optics, Volume. 44, Issue 1, 93(2023)
Particles image detection based on Mask R-CNN combined with edge segmentation
Figures & Tables(13)
Fig. 2. Structure diagram of Denseblock module and channel attention module
Fig. 6. Loss curves of training process of different backbone networks
Fig. 8. Size distribution of different networks detection on test set
Table 1. Detection accuracy of different backbone networks
View tableView in ArticleTable 1. Detection accuracy of different backbone networks
主干网络 样本集1AP 样本集2AP 样本集3AP 网络权重大小/MB ResNet 0.972453729 0.96582670 0.968745449 106 DenseNet 0.953721519 0.92923514 0.952060297 29.5 DenseAttention 0.976117450 0.94481288 0.963881690 30.8
Table 2. IoU comparison before and after improvement
View tableView in ArticleTable 2. IoU comparison before and after improvement
样本集 ResNet 原模型 DenseNet 原模型 DenseAtt 原模型 ResNet 改进模型 DenseNet 改进模型 DenseAtt 改进模型 样本集1 0.714810 0.662648 0.714638 0.872522 0.849003 0.866694 样本集2 0.684141 0.654970 0.698584 0.841869 0.836759 0.843355 样本集3 0.718732 0.669550 0.710328 0.852613 0.837046 0.833949
Table 3. Mean detection time of different networks
s View tableView in ArticleTable 3. Mean detection time of different networks
s 样本集 ResNet 原模型 DenseNet 原模型 DenseAtt 原模型 ResNet 改进模型 DenseNet 改进模型 DenseAtt 改进模型 样本集1 0.508924 0.556057 0.558442 0.688702 0.703527 0.726827 样本集2 0.608456 0.634376 0.663617 0.934323 0.930722 0.991752 样本集3 0.659190 0.677558 0.680201 0.926070 0.935717 0.951665
Table 4. Statistical standard deviation of particles accumulative proportion error of different methods
View tableView in ArticleTable 4. Statistical standard deviation of particles accumulative proportion error of different methods
方法 样本集1 样本集2 样本集3 Canny 0.270028 0.243427 0.154735 Watershed 0.223609 0.207637 0.155501 UNet 0.256473 0.228826 0.183079 UNet+Watershed 0.300005 0.261020 0.220387 ResNet+原模型 0.158070 0.153285 0.120736 DenseNet+原模型 0.368956 0.348426 0.255952 DenseAtt+原模型 0.149885 0.143315 0.109891 ResNet+改进掩膜 0.013807 0.025567 0.012105 DenseNet+改进掩膜 0.040248 0.040512 0.024433 DenseAtt+改进掩膜 0.018250 0.030876 0.006074
Table 5. Correlation of size distribution between different methods
View tableView in ArticleTable 5. Correlation of size distribution between different methods
方法 样本集1 样本集2 样本集3 Canny 0.199998 0.439937 0.642170 Watershed 0.285612 0.542120 0.627450 UNet 0.128555 0.344368 0.438553 UNet+Watershed 0.087232 0.287599 0.278089 ResNet+原模型 0.611606 0.574975 0.694612 DenseNet+原模型 0.431583 0.494701 0.610243 DenseAtt+原模型 0.640869 0.648856 0.780750 ResNet+改进掩膜 0.935148 0.894378 0.983772 DenseNet+改进掩膜 0.783157 0.860752 0.969065 DenseAtt+改进掩膜 0.940563 0.940095 0.991209
Tools
Get Citation
Copy Citation Text
Xuan LI, Zhou YANG, Xinyu TAO, Xiaojie WANG, Xutao MO, Xianshan HUANG. Particles image detection based on Mask R-CNN combined with edge segmentation[J]. Journal of Applied Optics, 2023, 44(1): 93
Paper Information
Category: Research Articles
Received: Jan. 22, 2022
Accepted: --
Published Online: Feb. 22, 2023
The Author Email: HUANG Xianshan (Huangxs@ahut.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20