Tongue Image Detection Algorithm Based on Improved YOLOv5 Network
Aiming at the problem of false detection and missed detection of tongue image in the natural state of the current tongue image detection model,we propose a tongue image detection algorithm based on YOLOv5 in the natural state with the collected tongue image as the research object.Firstly,the original SiLU activation function is replaced with the ReLu activation function to reduce the exponential operation and accelerate the convergence of the tongue image detection network.Then,Ghost lightweight module technology is used to greatly reduce the number of parameters of the tongue detection network.Finally,the SimAm attention mechanism is integrated into the feature extraction network to obtain tongue features,and the tongue features are fused from multiple dimensions to reduce the influence of the natural environment on the extraction of tongue features.A lightweight tongue image detection model is obtained,which can be analyzed on the self-made dataset:the weight of the lightweight detection model reaches7.8 MB,the detection accuracy reaches96.6%,and the number of frames per second is as high as 86 frames,which is more suitable for the collection of tongue images in the natural state.The experimental results show that compared with other commonly used detection algorithms,the performance index of the improved tongue image detection network has been improved to different degrees,and the detection effect of tongue image is better.
万方数据
维普
