Crystal Morphology Monitoring based on In-situ Image Analysis of L-glutamic Acid Crystallization

DOI

10.2991/cnci-19.2019.53How to use a DOI?

Keywords

Crystal, image analysis, I-BGLAM, image descriptors, segmentation

Abstract

In the process of chemical industry and biological pharmacy, the morphology of the crystal plays a vital role, different morphological characteristics such as shape and size have a direct impact on production. Therefore, this paper proposes a synthetic in-situ image analysis method for monitoring the morphology of crystals based on using an invasive imaging system. The proposed method includes image preprocessing, feature extraction, morphological identification and agglomeration re-segmentation. The in-situ image is first pre-processed to eliminate the effects of water droplets, particle shadows, and uneven illumination. Then, texture features are extracted by using Improved-Basic Gray Level Aura Matrix (I-BGLAM) for different types of particles, and shape features are extracted by using image descriptors. Afterwards, the extracted features are used to morphologically identify the different particles. At last, the salient corners of the particles are detected, and a segmentation algorithm that separates individual crystals from the agglomerates is constructed by clustering the same type of salient corners. The case study and experimental results of L-glutamic acid cooling crystallization show that the image analysis method can be effectively used for morphology analysis of in-situ crystals with good precision.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhimao Lu
AU  - Lin Zhang
AU  - Yongming Jiang
AU  - Chi Zhang
AU  - Guijuan Zhang
AU  - Mengzhu Liu
PY  - 2019/05
DA  - 2019/05
TI  - Crystal Morphology Monitoring based on In-situ Image Analysis of L-glutamic Acid Crystallization
BT  - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)
PB  - Atlantis Press
SP  - 371
EP  - 390
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnci-19.2019.53
DO  - 10.2991/cnci-19.2019.53
ID  - Lu2019/05
ER  -