Abstract: Embodiments of the present application provide an image retrieval method, device, and electronic device. In the method, a query image is acquired; a target feature of the query image is determined based on a pre-trained deep neural network; wherein the deep neural network is obtained by training according to respective sample images and predetermined features, which can form the target feature, corresponding to the respective sample images; target features of a plurality of images to be retrieved is obtained; a similarity between the target feature of the query image and the target feature of each image to be retrieved is calculated; a retrieval image corresponding to the query image is determined from the plurality of images to be retrieved according to the calculated similarities.

Abstract: Embodiments of the present application provide an image retrieval method, device, and electronic device, wherein the method includes: acquiring a query image; determining a target feature of the query image based on a pre-trained deep neural network; wherein the deep neural network is obtained by training according to respective sample images and predetermined features, which can form the target feature, corresponding to the respective sample images; obtaining target features of a plurality of images to be retrieved; calculating a similarity between the target feature of the query image and the target feature of each image to be retrieved; determining a retrieval image corresponding to the query image from the plurality of images to be retrieved according to the calculated similarities. The image retrieval method, device, and electronic device provided by the embodiments of the present application can improve the accuracy of image retrieval.

Abstract: An image retrieval method and system are provided.