Recognition Methods for Coal and Coal Gangue Based on Deep Learning

Recognizing coal and gangue is an important part of the industry mainly conducted via human sorting at present. Consequently, considerable manpower needed, which adds a burden to enterprises results in low efficiency. As branch artificial intelligence, deep learning has been widely applied many fields, especially machine vision voice recognition, its performance greatly improved compared with performances traditional methods, it also good transfer ability. This paper proposed YOLOv4 algorithm as classic method for intelligent highly accurate recognition gangue. Compared other algorithms, better anchor value by applying cluster analysis different data sets, anti-interference ability due using Laplacian operator Gaussian filter reduce impacts from mine dust shock acquires richer detailed information increasing number layers feature pyramid. The experimental show that four algorithms YOLOv4, YOLOv3, SSD Faster-RCNN, this exhibits detection accuracy, speed robust performance.