多模型加权融合机制的石墨纯度识别

Graphite Purity Identification Based on Multi Model Weighted Fusion Mechanism

针对人工识别的效率低及单一卷积神经网络提取特征的遗漏问题,提出了多模型加权融合机制的石墨纯度识别算法.在自建小样本数据集上,进行离线扩充和在线增强,提高模型的泛化能力,减少深层CNN的过拟合问题;结合迁移学习,利用优化的AlexNet和ResNet50构建双通道卷积神经网络,提取石墨图像的深层次特征,并将两者的特征进行加权融合后,使用SoftMax分类器进行分类.实验结果表明,经过加权融合后的识别准确率均优于单一网络,达到97.94%,同时模型的稳定性增强,收敛速度加快,证明了所提算法的可行性与有效性.

In view of the low efficiency of manual recognition and the omission of features extracted by single convolution neural network,a graphite purity recognition algorithm based on multi-model weighted fusion mechanism is proposed.On the self-built small sample data set,offline expansion and online enhancement are carried out to improve the generalization ability of the model and reduce the over fitting problem of deep CNN;combined with transfer learning,a dual channel convolution neural network is constructed by using the optimized AlexNet and ResNet50 to extract the deep features of graphite image,and after the features of the two are weighted and fused,the Soft Max classifier is used for classification.The experimental results show that the recognition accuracy after weighted fusion is better than that of single net-work,reaching 97.94%.At the same time,the stability of the model is enhanced and the convergence speed is accelerated,which proves the feasibility and effectiveness of the proposed algorithm.