Optimization of image processing parameters for large sets of in-process video microscopy images acquired from batch crystallization processes: Integration of uniform design and simplex search

Abstract A narrow particle size distribution with desired particle shape usually characterizes the expected product quality for pharmaceutical crystallization processes. Real-time estimation of particle size and shape from in-process video images is emerging as a new process analytical technology (PAT) tool for crystallization process monitoring and control. Any image processing algorithm involves a number of user-defined parameters and, typically, optimal values for these parameters are manually selected. Manual selection of optimal image processing parameters may become complex, time-consuming and unfeasible when there are a large number of images and particularly if these images are of varying qualities, as could happen in batch crystallization processes. This paper combines two optimization approaches to systematically locate optimal sets of image processing parameters — one approach is a model-based optimization method in conjunction with uniform experimental design; another approach is the Sequential Simplex Optimization method. Our study shows that these two approaches or a combination of them can successfully locate the optimal sets of parameters and the image processing results obtained with these parameters are better than those obtained via manual tuning. Combination of these two approaches also helps to overcome the drawbacks of each individual method. Our work also demonstrates that the optimal sets of parameters obtained from one batch of process images can also be successfully applied to another batch of process images that are obtained from the same system. The in-process video microscopy (PVM) images that are acquired from Monosodium Glutamate (MSG) seeded cooling crystallization process are used to demonstrate the workability of the proposed approach.

[1]  James B. Rawlings,et al.  Particle-shape monitoring and control in crystallization processes , 2001 .

[2]  Wen Wu,et al.  Experimental designs for optimisation of the image analysis process for cDNA microarrays , 2005 .

[3]  章 毓晋,et al.  Advances in image and video segmentation , 2006 .

[4]  J. Sneddon Sequential simplex optimization , 1992 .

[5]  Mehmet Tolga Taner,et al.  Taguchi's experimental design method on improvement of medical image quality. , 2007, Leadership in health services.

[6]  Song Mao,et al.  Empirical Performance Evaluation Methodology and Its Application to Page Segmentation Algorithms , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Kevin J. Roberts,et al.  Multi-scale segmentation image analysis for the in-process monitoring of particle shape with batch crystallisers , 2005 .

[8]  Charles V. Jakowatz,et al.  Shift–Scale Complex Correlation for Wide-Angle Coherent Cross-Track SAR Stereo Processing , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[9]  Hsin-Hung Chen,et al.  An algorithm of image processing for underwater range finding by active triangulation , 2004 .

[10]  Raghuraj K. Rao,et al.  Genetic Programming Based Variable Interaction Models for Classification of Process and Biological Systems , 2009 .

[11]  Matthias F. Carlsohn Spectral imaging in real-time - Imaging principles and applications , 2005, Real Time Imaging.

[12]  Paul Marsden,et al.  Accurate attenuation correction in PET using short transmission scans and consistency information , 2001 .

[13]  James B. Rawlings,et al.  Model-based object recognition to measure crystal size and shape distributions from in situ video images , 2007 .

[14]  Domingos Dellamonica,et al.  An Exact Algorithm for Optimal MAE Stack Filter Design , 2007, IEEE Transactions on Image Processing.

[15]  Ying Zhou,et al.  Critical evaluation of image processing approaches for real-time crystal size measurements , 2009, Comput. Chem. Eng..

[16]  Debasis Sarkar,et al.  In situ particle size estimation for crystallization processes by multivariate image analysis , 2009 .

[17]  Yizeng Liang,et al.  Uniform design and its applications in chemistry and chemical engineering , 2001 .

[18]  Kevin J. Roberts,et al.  Real-time product morphology monitoring in crystallization using imaging technique , 2005 .

[19]  Sylvie Treuillet,et al.  Design of Experiments for Performance Evaluation and Parameter Tuning of a Road Image Processing Chain , 2006, EURASIP J. Adv. Signal Process..

[20]  J. Macgregor,et al.  Digital Imaging for Online Monitoring and Control of Industrial Snack Food Processes , 2003 .

[21]  Masakazu Ejiri,et al.  An Automatic Wafer Inspection System Using Pipelined Image Processing Techniques , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Moncef Chaabouni,et al.  The use of the simplex method and its derivatives to the on-line optimization of the parameters of an injection moulding process , 2009 .

[23]  G. O. Verran,et al.  DOE applied to optimization of aluminum alloy die castings , 2008 .

[24]  Ludwik Kurz,et al.  An experimental design approach to image enhancement , 1992, IEEE Trans. Syst. Man Cybern..

[25]  Konstantina S. Nikita,et al.  Automatic retinal image registration scheme using global optimization techniques , 1999, IEEE Transactions on Information Technology in Biomedicine.

[26]  Graziano Chesi,et al.  Camera Displacement via Constrained Minimization of the Algebraic Error , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[27]  Takayuki Itoh,et al.  A novel multi-dimensional visualization technique for understanding the design parameters of drug formulations , 2010, Comput. Chem. Eng..

[28]  James B. Rawlings,et al.  An algorithm for analyzing noisy, in situ images of high-aspect-ratio crystals to monitor particle size distribution , 2006 .

[29]  J. Rawlings,et al.  Industrial crystallization process control , 2006, IEEE Control Systems.

[30]  Xiaobo Zhou,et al.  Registration of 3-D CT and 2-D Flat Images of Mouse via Affine Transformation , 2008, IEEE Transactions on Information Technology in Biomedicine.

[31]  Kevin J. Roberts,et al.  Classifying organic crystals via in-process image analysis and the use of monitoring charts to follow polymorphic and morphological changes , 2005 .