Determining similarity of images using multidimensional hash vectors corresponding to the images

摘要

A method of searching for similar images is performed at a computing system having one or more processors and memory. The method includes receiving an input image having content, and generating a feature vector corresponding to the input image according to a trained classifier model. The feature vector has multiple components. The method further includes encoding the feature vector as a similarity hash by quantizing each component. The method also includes, for each reference image in a plurality of reference images: obtaining a reference hash for the reference image; computing similarity between the input image and the reference image by computing a distance between the reference hash and the similarity hash; and determining whether the computed distance is within a predetermined threshold. When the computed distance is within the predetermined threshold, the computing system returns the reference image as an image that is similar to the input image.