Research on the application of an improved deep convolutional neural network in image recognition

摘要

Aiming at the problems of the classic convolutional neural network with fewer convolutional layers, fixed convolution kernel size, and fewer features extracted, this paper proposes an improved deep convolutional neural network model, which different convolution kernels can be assigned to perform convolution operations according to the different amount of information in the image area, so it can better extract the effective information of the image and is more suitable for the recognition of complex images. Experiment shows that a higher recognition rate can be obtained.