(中南大学 资源与安全工程学院，长沙 410083)
摘 要: 黑钨矿图像识别是代替黑钨选矿手选抛废的一条高效途径，但存在无法识别黑钨矿石与围岩废石的问题。本文利用深度学习中卷积神经网络进行迁移学习来解决，该方法具有收敛快速、所需数据集小和分类准确的优点。首先，对黑钨原矿彩色图像采用旋转、平移等方法进行数据增广降低样本不平衡性。其次，基于Keras框架使用本文优化的神经网络进行全新训练。结果表明：黑钨矿石与围岩两类识别中Wu-VGG19迁移网络矿石识别率最高，为97.51%。此外，本文加入石英脉石类别继续实验，得出修改的Wu-v3迁移网络矿石识别率最高，为99.6%。
关键字: 黑钨矿选矿；迁移学习；深度学习；图像识别；卷积神经网络
（School of Resources and Safety Engineering, Central South University, Changsha 410083, China）
Abstract:Wolframite image recognition is an efficient way to replace concentrator for manual sorting, but the problem is that the wolframite and surrounding rock cannot be recognized. In this paper, convolutional neural network in deep learning was used to solve the problem. This method is fast convergence, small data set and accurate classification. Firstly, the RGB image of wolframite was augmented by rotation and translation to reduce sample imbalance. Secondly, the neural network optimized in this paper is used for new training based on Keras framework. Finally, the results show that Wu-VGG19 has the highest recognition rate of 97.51% in wolframite and surrounding rock recognition. In addition, quartz gangue category is added to continue the experiment, and the final result shows that the improved Inception Wu-v3 has the highest ore recognition rate, 99.6%.
Key words: wolframite beneficiation; transfer learning; deep learning; image recognition; convolutional neural network
