Infrared and Laser Engineering, Volume. 50, Issue 10, 2021G004(2021)
Particle auto-statistics and measurement of the spherical powder for 3D printing based on deep learning
Fig. 1. Flowchart of the powder microscopy image automatic analysis system
Fig. 2. (a) Original SEM image (2 048×2 048 pixel), which is cropped into 16 parts; (b) Characteristic image labeled with LabelMe(512×512 pixel); (c) The corresponding image mask of (b)
Fig. 3. Loss-epoch curve during train process
Fig. 4. Flowchart of transferring and rough merging process of one sub-image
Fig. 5. Illustration of two kinds of IoU & IoS in rough merging and precise merging processes, respectively. (a) IoU & IoS of two circumscribed rectangles; (b) IoU & IoS of two masks; (c) One example of the usage of IoS
Fig. 6. (a) Illustration of particle boundary smoothing and error compensation; (b) Fitted perimeter and area residual function based on scattered deviation values of standard circles
Fig. 7. Predicted results and comparation with the Phenom ProSuite Software Particlemetric. (a) Raw image; (b) Output segmentation result of Particlemetric; (c) Four enlarged details region of (b); (d) Output result of proposed method; (e) Four enlarged details region of (d)
Fig. 8. Statistical analysis results and comparation. (a) PSD results measured by the Particlemetric, our method and laser diffraction technique, respectively; (b) Degree of sphericity distribution (DSD) results measured by Particlemetric and proposed method
Get Citation
Copy Citation Text
Yichao Wang, Zheng Zhang, Haizhou Huang, Wenxiong Lin. Particle auto-statistics and measurement of the spherical powder for 3D printing based on deep learning[J]. Infrared and Laser Engineering, 2021, 50(10): 2021G004
Category: Image processing
Received: Jun. 10, 2021
Accepted: --
Published Online: Dec. 7, 2021
The Author Email: