Using Convolutional Neural Networks to Develop State-of-the-Art Flotation Froth Image Sensors

Abstract Convolutional neural networks provide a state-of-the-art approach to the development of froth image sensors. In this study, it is shown that a pretrained neural network architecture, namely VGG16, can be used to obtain significant improvements in froth image sensors. However, training of these networks is computationally demanding and require large data sets that may not be readily available. These problems can be circumvented by making use of transfer learning and partial retraining of the network. Likewise, minor modification of the network architecture can also expedite the development of the models. This is demonstrated in a case study involving an image data set from an industrial platinum group metals plant.

[1]  Jiri Matas,et al.  Systematic evaluation of convolution neural network advances on the Imagenet , 2017, Comput. Vis. Image Underst..

[2]  D. La Rosa,et al.  A correlation between Visiofroth(TM) measurements and the performance of a flotation cell , 2007 .

[3]  Paul F. Whelan,et al.  Using filter banks in Convolutional Neural Networks for texture classification , 2016, Pattern Recognit. Lett..

[4]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[5]  Hiba Chougrad,et al.  Deep Convolutional Neural Networks for breast cancer screening , 2018, Comput. Methods Programs Biomed..

[6]  Jan J. Cilliers,et al.  A review of froth flotation control , 2011 .

[7]  Gilson A. Giraldi,et al.  Convolutional Neural Network approaches to granite tiles classification , 2017, Expert Syst. Appl..

[8]  Ausif Mahmood,et al.  Improved Gait recognition based on specialized deep convolutional neural networks , 2015, 2015 IEEE Applied Imagery Pattern Recognition Workshop (AIPR).

[9]  Guangyuan Xie,et al.  The concentrate ash content analysis of coal flotation based on froth images , 2016 .

[10]  Dongyang Dou,et al.  Ash content prediction of coarse coal by image analysis and GA-SVM , 2014 .

[11]  Chris Aldrich,et al.  The estimation of platinum flotation grade from froth image features by using artificial neural networks. , 2010 .

[12]  Ian K. Craig,et al.  On the current state of flotation modelling for process control , 2017 .

[13]  Melvyn L. Smith,et al.  Towards on-farm pig face recognition using convolutional neural networks , 2018, Comput. Ind..

[14]  Chris Aldrich,et al.  Estimation of platinum flotation grades from froth image data , 2011 .

[15]  Iasonas Kokkinos,et al.  Deep Filter Banks for Texture Recognition, Description, and Segmentation , 2015, International Journal of Computer Vision.

[16]  Carlo Meghini,et al.  Deep learning for decentralized parking lot occupancy detection , 2017, Expert Syst. Appl..

[17]  Chris Aldrich,et al.  Digital image processing as a tool for on-line monitoring of froth in flotation plants , 1994 .

[18]  Jani Kaartinen,et al.  Machine-vision-based control of zinc flotation—A case study , 2006 .

[19]  Chris Aldrich,et al.  Froth image analysis by use of transfer learning and convolutional neural networks , 2018 .

[20]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

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

[22]  Olaf Hellwich,et al.  Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology , 2017, Comput. Medical Imaging Graph..

[23]  Chris Aldrich,et al.  Online monitoring and control of froth flotation systems with machine vision: A review , 2010 .