Chinese Journal of Liquid Crystals and Displays, Volume. 37, Issue 8, 972(2022)
High-throughput blue phase liquid crystal recognition based on convolutional neural network
Fig. 1. Partial liquid crystal phase state images under polarized light microscope (left)and in the data set (right）.(a1）~(a2)Images of isotropic phase； (b1）~(b2)Images of blue phase； (c1）~(c2)Images of cholesteric Phase.
Fig. 2. Flow chart of high-throughput blue phase liquid crystal recognition
Fig. 4. Loss (a) and accuracy rate (b) change graph of model training.
Fig. 5. (a) Basic framework of Labview2018 calls python interface； (b) Display of each pin of Python node.
Fig. 6. Result of calling the model to identify a single sample phase state.The figure shows the recognition result and probability，BP means blue phase，1.0 means the probability of the recognition result being blue phase is close to 1.
Fig. 7. High throughput classification accuracy confusion matrix of liquid crystal phase states
Get Citation
Copy Citation Text
Ya-qian ZHANG, Yong-feng CUI, Hao WANG, Wan-li HE, Lei ZHANG, Zhou YANG, Hui CAO, Dong WANG, Yu-zhan LI. High-throughput blue phase liquid crystal recognition based on convolutional neural network[J]. Chinese Journal of Liquid Crystals and Displays, 2022, 37(8): 972
Category: Research Articles
Received: Dec. 1, 2021
Accepted: --
Published Online: Aug. 15, 2022
The Author Email: Wan-li HE (hewanli@mater.ustb.edu.cn)
