Hand heat trace recognition based on attention mechanism and residual networks
Infrared image recognition of hand thermal trace is of great significance to criminal investigation,but thermal trace images often have fuzzy problems.Traditional recognition methods rely on artificial design features,and conventional deep learning methods depend on the number of samples,so it is difficult to apply them directly.Using the strong feature expression ability of con-volutional neural network,the residual network is introduced to enhance the performance of learning features of the model,and the attention mechanism module is designed to improve the attention of the model to important features from the spatial and channel di-mensions.Finally,the residual convolutional neural network based on attention mechanism is constructed.Experimental results verify the effectiveness of the algorithm and achieve the highest recognition accuracy.
NETL
NSTL
万方数据
