Image processing method and system based on local binary convolution, and storage medium

The invention relates to an image processing method and system based on local binary convolution, and a storage medium. Comprising the following steps: acquiring a to-be-processed original image, and carrying out characterization reprocessing on the original image to obtain an initial feature map; constructing a local binary convolution model according to a binary neural network, carrying out binarization processing on the initial feature map through the binary convolution model, and obtaining a binarized feature map; using a central pixel as a local threshold value for neighborhood pixels in the binarized feature map, and collecting to obtain high-order image statistical information; and identifying the high-order image statistical information through a binary neural network to realize image processing of local binary convolution. According to the method, the accuracy of the BNN structure is improved, and the method can effectively capture high-order image statistical information with maximized information r