Coal damage type rapid identification method and device based on deep learning technology

The invention discloses a coal damage type rapid identification method and device based on a deep learning technology. The method comprises: acquiring a damage type image of coal; carrying out image preprocessing, wherein the coal damage type image recognition model is a residual convolutional neural network image recognition model based on deep learning and comprises five structures including aninput layer, a convolution layer, a pooling layer, a full connection layer and an output layer, and consists of one input layer, 49 convolution layers, two pooling layers, one full connection layer and one output layer; training a damage type image recognition model of the coal, recognizing the damage type image of the coal, and obtaining the damage type to which the image of the coal belongs. According to the method, the damage type of the coal can be quantitatively, safely, quickly and accurately identified. 本发明公开了一种基于深度学习技术的煤的破坏类型快速识别方法及装置，包括采集煤的破坏类型图像，图像预处理，煤的破坏类型图像识别模型是基于深度学习的残差卷积神经网络图像识别模型，包括输入层、卷积层、池化层、全连接及输出层5