Monitoring sugar crystallization with deep neural networks

Abstract Human labor still play an important role in cane sugar crystallization process. Automation control is essential to reduce human labor. An accurate image classification system is the basis for automation control of the cane sugar crystallization process. This paper builds a deep learning framework based on deep convolutional neural networks (DCNNs) to classify cane sugar crystallization image of cane sugar crystallization process for sugar factory. Different networks were trained on a large image data set obtained from a sugar batch crystallizer. Based on the data set, the established model was used to classify cane sugar crystallization image. The classification accuracy of the proposed model reached 0.901. The confusion matrix of the InceptionResNetV2 model indicates classification accuracy of between 0.83 and 0.99 are achieved in classifying cane sugar crystal images from a cane sugar factory into 5 categories. This provides a promising means for the future development of monitoring systems using image. The proposed DCNNs model was compared against other models, such as, Inception-V3, ResNet50, and a simple DCNNs. The experimental results showed that the deep learning framework outweighs other models and can serve as a benchmark of monitoring cane sugar crystallization using DCNNs in sugar industry.

[1]  Kipton Barros,et al.  Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning , 2019, Nature Communications.

[2]  Khurram Yousaf,et al.  Tomato volume and mass estimation using computer vision and machine learning algorithms: Cherry tomato model , 2019 .

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

[4]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Ian Witten,et al.  Data Mining , 2000 .

[6]  K. Van Den Abeele,et al.  Development of an ultrasonic shear reflection technique to monitor the crystallization of cocoa butter. , 2015, Food research international.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Nikolaos Doulamis,et al.  Deep Learning for Computer Vision: A Brief Review , 2018, Comput. Intell. Neurosci..

[9]  Y. Meng,et al.  Hybrid modeling based on mechanistic and data-driven approaches for cane sugar crystallization , 2019, Journal of Food Engineering.

[10]  Yu Zhang,et al.  Very deep convolutional networks for end-to-end speech recognition , 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Syed Jawad Hussain Shah,et al.  Visual features based automated identification of fish species using deep convolutional neural networks , 2019, Comput. Electron. Agric..

[12]  Kevin M. Ryan,et al.  Crystal Structure Prediction via Deep Learning. , 2018, Journal of the American Chemical Society.

[13]  R. Giegé,et al.  Monitoring protein crystallization by dynamic light scattering , 1989 .

[14]  Sanket A. Deshmukh,et al.  Machine-Learning Based Stacked Ensemble Model for Accurate Analysis of Molecular Dynamics Simulations. , 2019, The journal of physical chemistry. A.

[15]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[16]  Robert Amelard,et al.  A new take on measuring nutritional density: The feasibility of using a deep neural network to assess commercially-prepared puree concentrations , 2017, ArXiv.

[17]  W. Wilson.  Monitoring crystallization experiments using dynamic light scattering: Assaying and monitoring protein crystallization in solution , 1990 .

[18]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[19]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[20]  Jun Wang,et al.  Rapid identification of tea quality by E-nose and computer vision combining with a synergetic data fusion strategy , 2019, Journal of Food Engineering.

[21]  Eliseo Hernandez-Martinez,et al.  Indirect Monitoring Cane Sugar Crystallization via Image Fractal Analysis , 2018, Computación y Sistemas.

[22]  Matthijs Douze,et al.  Fixing the train-test resolution discrepancy , 2019, NeurIPS.

[23]  J. Ulrich,et al.  Metastable zone determination of lipid systems: ultrasound velocity versus optical back-reflectance measurements. , 2010 .

[24]  Yang Song,et al.  Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[26]  Alexandr A. Kalinin,et al.  Albumentations: fast and flexible image augmentations , 2018, Inf..

[27]  Jose Alvarez-Ramirez,et al.  Characterization of cane sugar crystallization using image fractal analysis , 2010 .

[28]  M. Bahrami,et al.  Measurement of Morphological Characteristics of Raw Cane Sugar Crystals Using Digital Image Analysis , 2015 .

[29]  J. Casci,et al.  Use of pH-measurements to monitor zeolite crystallization , 1983 .

[30]  Mostafa Khojastehnazhand,et al.  Machine vision system for classification of bulk raisins using texture features , 2020 .

[31]  David F. Noble.  Forces of production : a social history of industrial automation , 1984 .

[32]  Weiguo Fan,et al.  A new image classification method using CNN transfer learning and web data augmentation , 2018, Expert Syst. Appl..

[33]  Z. Nagy,et al.  Application of laser backscattering for monitoring of palm oil crystallisation from melt , 2011 .

[34]  Huifang Deng,et al.  Medical Image Classification Based on Deep Features Extracted by Deep Model and Statistic Feature Fusion with Multilayer Perceptron‬ , 2018, Comput. Intell. Neurosci..

[35]  Susan L. Lane,et al.  At-line near-infrared spectroscopy for prediction of the solid fat content of milk fat from New Zealand butter. , 2007, Journal of agricultural and food chemistry.

[36]  M. Wolcott,et al.  Using dynamic mechanical spectroscopy to monitor the crystallization of PP/MAPP blends in the presence of wood , 2000 .

[37]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[38]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.

[39]  Y. Man,et al.  MONITORING CRYSTAL DEVELOPMENT IN PALM OIL-BASED FLUID SHORTENING PRODUCTION BY FT-IR SPECTROSCOPY , 2010 .

[40]  M. Scheffler,et al.  Insightful classification of crystal structures using deep learning , 2017, Nature Communications.

[41]  P. Rein.  Cane Sugar Engineering , 2007 .

[42]  Geoffrey E. Hinton,et al.  Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer , 2017, ICLR.

[43]  Janet Newman,et al.  Classification of crystallization outcomes using deep convolutional neural networks , 2018, PloS one.

[44]  Zihao Liu,et al.  Soft-shell Shrimp Recognition Based on an Improved AlexNet for Quality Evaluations , 2020 .