Classification of Mineral Foam Flotation Conditions Based on Multi-Modality Image Fusion

Accurate and rapid identification of mineral foam flotation states can increase utilization reduce the consumption reagents. The traditional process concentrates on extracting features from a single-modality image, accuracy is undesirable once problems such as insufficient image clarity or poor boundaries are encountered. In this work, classification method based multi-modality fusion CNN-PCA-SVM proposed for work condition recognition visible infrared gray images. Specifically, images fused in non-subsampled shearlet transform (NSST) domain using parameter adaptive pulse coupled neural network (PAPCNN) quality detection high low frequencies, respectively. convolution (CNN) used trainable feature extractor to images, principal component analysis (PCA) reduces data, support vector machine (SVM) recognizer classify condition. After experiments, model fuse recognize with accuracy.