A synthetic image analysis method is proposed for in-situ detection of particle agglomeration for monitoring crystallization processes, based on using a non-invasive imaging system. The proposed method consists of image pre-processing, feature analysis, shape identification, and re-segmentation. Firstly, in-situ captured images are pre-processed to eliminate the influence from uneven illumination background and particle motion. Then, based on choosing the fundamental image features of needle-like crystals, a texture computation algorithm is established with a gray level co-occurrence matrix (GLCM) defined for different particle types. Subsequently, a shape identification algorithm is given to distinguish the primary particles from overlapped particles in a captured image. Finally, a re-segmentation algorithm is constructed to separate individual crystals from the overlapped crystals, by using a geometric approach and the chord-to-point distance accumulation (CPDA) technique, and then pseudo agglomerates are recognized from the overlapped crystals based on the texture analysis. Experimental results on the cooling crystallization of β form L-glutamic acid well demonstrate the effectiveness of the proposed image analysis method.
|Title of host publication||2017 36th Chinese Control Conference (CCC)|
|Number of pages||6|
|Publication status||Published - 11 Sep 2017|
|Name||Chinese Control Conference|
- image analysis
- texture feature