A Method Based on Minimum Error Thresholding for Froth Image Classification

A classification method based on minimum error thresholding was proposed for the difficulty in classification of froth images. The optimal thresholds were determined by minimum error thresholding for binarizing the original froth images. The bubble area features of the binary images were extracted and then classified with the support vector machine (SVM). The experimental results show that the proposed method is simple and practical and can classify the froth images effectively.