基于深度学习的复杂分拣图像快速识别方法研究

Research on rapid recognition of complex sorting images based on deep learning

训练速度更快、识别精准度更高的图像识别技术一直是智能技术的研究热点及前沿。针对物流分拣仓库环境复杂、照明度不高以及快递外包装区别不明显的特点,对基于深度学习的分拣图像快速识别进行了研究,设计了一个卷积神经网络。由于仓库的封闭环境和光照条件等因素而导致分拣图像不是很清晰,首先用对偶树复小波变换对其进行降噪等预处理;然后在基于AlexNet神经网络的基础上,对于卷积神经网络的卷积层、ReLU层和池化层参数进行重新定义来加快神经网络的学习速度;最后根据新的图像分类任务对神经网络的最后三层全连接层、Softmax层和分类输出层进行定义来适应新的图像识别。所提出的基于深度学习的快速分拣图像识别方法在面对较为复杂的分拣图像识别时,有较高的训练速度和识别精准度,能达到实验要求。分拣图像快速识别对于提高无人仓等场合下的物流效率具有重要意义。

Image recognition technology with faster training speed and higher recognition accuracy has always been the focus and frontier of intelligent technology research.Sorting image fast recognition is of great significance to improve logistics efficiency in unmanned warehouse and other occasions.The simulation of sorting image fast recognition based on deep learning is studied.A convolution neural network is designed.For the specific environment of logistics warehouse and the specified objects to be identified,the sorting image is not very clear because of the closed environment and illumination conditions of warehouse.Firstly,the dual tree complex wavelet transform is used to denoise the sorting image.Then,on the basis of AlexNet neural network,the convolution layer of convolution neural network is dealt with.ReLU layer and pooling layer parameters are redefined to speed up the learning speed of the neural network.Then,according to the new image classification task,the last three layers of the neural network are defined,which are full connection layer,Softmax layer and classification output layer,to adapt to the new image recognition.The proposed fast sorting image recognition technology based on depth learning has higher training speed and recognition accuracy in the face of more complex sorting image recognition.