THE CLASSIFICATION OF FROTH STRUCTURES IN A COPPER FLOTATION PLANT BYMEANS OF A NEURAL-NET

after revisionBy making use of grey Level dependence matrix methods, d igitized images of the froth phases in a copper flotation plant were r educed to feature vectors without losing essential information of the characteristics of the froth. Classification of features extracted by means of both spatial grey level dependence matrix (SGLDM) methods, as well as neighbouring grey level dependence matrix (NGLDM) methods was investigated. By using a learning vector quantization (LVQ) neural ne t it was shown that froth structures could be classified satisfactoril y when either NGLDM or SGLDM methods were used. When these feature set s were combined, however, the success rate of classification improved to almost 90%. This is sufficiently accurate to enable incorporation o f the neural net classifier into on-line plant control systems.