R-K algorithm: A novel Dynamic Feature Matching Method of flotation froth

Abstract Froth flotation is a common process used for extracting a desired mineral from its ore. The dynamic characteristics extraction towards froth flotation can better identify the collapse and fragmentation. According to the characteristics of continuous movement of flotation froth, a new flotation froth feature matching method is proposed, which based on Kalman filtering and RANSAC algorithm, called R-K matching algorithm. And then, combining the R-K matching algorithm and SURF (fast robust scale invariant feature extraction algorithm) to extract the dynamic characteristics of flotation froth. Finally, the velocity and the entropy of the flotation froth are calculated to confirm the effectiveness and the practicability. The simulation results from the industrial experimental data show that the method can extract more feature matching pairs than the existing methods. So, it can obtain more accurate dynamic information on flotation froth in the changed state.

[1]  Xiong Li,et al.  A fast threshold segmentation method for froth image base on the pixel distribution characteristic , 2019, PloS one.

[2]  Ang Su,et al.  Point-pattern matching method using SURF and Shape Context , 2013 .

[3]  M. Lu,et al.  A cascaded recognition method for copper rougher flotation working conditions , 2018 .

[4]  Ying Sun,et al.  Motion Estimation Via Cluster Matching , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Li Jianqi.  Flotation Froth Motion Velocity Extraction and Analysis Based on SIFT Features Registration , 2011 .

[6]  Henghua Shen,et al.  Adaptive registration algorithm of color images based on SURF , 2015 .

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

[8]  Mohammad Hamiruce Marhaban,et al.  Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks , 2014 .

[9]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[10]  M. Massinaei,et al.  Machine vision based monitoring and analysis of a coal column flotation circuit , 2019, Powder Technology.

[11]  Jianning Chi,et al.  Enhancing textural differences using wavelet-based texture characteristics morphological component analysis: A preprocessing method for improving image segmentation , 2017, Comput. Vis. Image Underst..

[12]  Jan J. Cilliers,et al.  The froth stability column : linking froth stability and flotation performance , 2005 .

[13]  Jan J. Cilliers,et al.  Dynamic froth stability in froth flotation , 2003 .

[14]  Mohammad Hamiruce Marhaban,et al.  An image segmentation algorithm for measurement of flotation froth bubble size distributions , 2017 .

[15]  Hui Zhang,et al.  Image Matching Based on Improved SIFT Algorithm , 2015 .

[16]  Zahra Hossein-Nejad,et al.  An adaptive image registration method based on SIFT features and RANSAC transform , 2017, Comput. Electr. Eng..