Gun image recognition method and system based on deep learning network

The invention belongs to the technical field of image recognition, and relates to a gun image recognition method and system based on a deep learning network, and the method comprises the following steps: S1, constructing a gun image data set, and carrying out the preprocessing of gun images in the gun image data set; s2, establishing a gun identification network model based on a Resnet18 network,wherein the gun identification network model is composed of a plurality of sections; s3, inputting a gun image with a known gun type, and training the gun identification network model to obtain a weight corresponding to each gun type; and S4, inputting a to-be-tested gun image into the trained gun identification network model to obtain a final gun category. According to the method, guns are classified by adopting a method of searching images by using images, the problems of various gun types, small appearance difference and influence on identification precision are solved, and automatic learning is carried out from me