摘要
为解决煤矿井下煤岩图像识别问题,本文研究了煤岩图像识别现状以及卷积神经网络在煤岩图像识别中的应用方式、存在问题和解决办法。通过对AlexNet网络进行迁移学习,将学习好的神经网络用于煤岩识别,并研究了不同网络对煤岩图像识别率、训练速度的影响。实验结果表明,本文方法能够取得较好的煤岩图像识别结果,为之后应用卷积神经网络解决煤岩图像识别问题提供了重要的参考价值。
In order to solve the problem of coal and rock image recognition in coal mine, this paper studies the current status of coal and rock image recognition, and the application methods, existing problems and solutions of convolutional neural network in coal and rock image recognition. Through the migration learning of the AlexNet network, a well-learned neural network is used for coal rock identification. The effects of different networks on the recognition rate and training speed of coal and rock images are studied. The experimental results show that the proposed method can obtain better image recognition results of coal and rock, and provides an important reference value for solving the problem of coal and rock image recognition by using convolutional neural network.
出处
《科技创新导报》
2019年第9期137-139,共3页
Science and Technology Innovation Herald