Image retrieval method based on combination of deep convolutional neural network and locality sensitive hash algorithm

The invention relates to the technical field of image retrieval, in particular to an image retrieval method based on the combination of a deep convolutional neural network and a locality sensitive hashing algorithm, which comprises the following steps of: S1, collecting a training set and a verification set in an open source data set of image retrieval; s2, during training, inputting a model; s3, testing a retrieval ranking; s4, a contrast loss function is adopted as a loss function of image retrieval, mP (at) k is added to a model evaluation index besides mAP, the image retrieval method based on the combination of the deep convolutional neural network and the local sensitive hashing algorithm is designed, image features of a galling library and a query library are extracted and obtained in a deep convolution mode, and the image retrieval efficiency is improved. LSH Hash coding is carried out, the retrieval performance is greatly improved, and the retrieval precision is greatly improved by using comparative l