基于卷积神经网络的物流货物图像分类研究

Research on Goods Image Classification Based on Convolutional Neural Network in Logistic Environment

基于卷积神经网络(CNN)针对物流环境下货物的图像分类问题进行了研究。首先,在实际物流环境下收集了13种货物的ROI图像,并通过每隔10°旋转的方式来扩充数据集以防止过拟合现象的发生;然后,在考虑了实际硬件条件的情况下构建了轻量级CNN,并进行了基于自建数据集的训练,训练实验发现,轻量级CNN模型具有很快的收敛速度并在验证集取得了100%的准确率;最后,研究了旋转对货物图像分类性能的影响,并进行了可视化分析,验证了CNN对旋转操作基本不具备一致性。

The classification of goods images in logistics environment based on convolutional neural networks has been studied.First,ROI images of 13 kinds of goods in logistics environment were collected and the data set was expanded by rotating every 10° to prevent overfitting.Then,a lightweight CNN was constructed and trained based on self-built data set considering the actual hardware conditions,and the training experiment showed that the model converged quickly and achieved 100% accuracy in the validation set.Finally,the effect of rotation on the classification performance of goods images was studied and performed a visual analysis,the result showed that CNN had poor invariance to rotation operation.