Image local feature extraction method and device

Abstract

The invention relates to an image local feature extraction method and device, and belongs to the technical field of image processing. The method comprises the following steps of constructing a Siamesenetwork; selecting an included angle cosine between the output feature vectors of the Siamese network as the similarity between the images; constructing an error function by using the similarity, training the Siamese network by using the sample image, and selecting the Siamese network with the minimum error as an image local feature extraction network; performing image block detection on the twoto-be-extracted whole images, combining the image blocks into image pairs, wherein each image pair comprises the image blocks belongs to the two images respectively, inputting the image pairs into theimage local feature extraction network, and selecting the matched image blocks as the local features of the to-be-extracted whole images. According to the method, the similarity of the image pairs iscalculated by adopting the included angle cosine between the feature vectors, the efficiency of selecting the matched image blocks is improved, and the image recognition efficiency is further improved.

Description

technical field [0001] The invention relates to an image local feature extraction method and device, belonging to the technical field of image processing. Background technique [0002] An image is a mapping of the real and complex world. It is essentially composed of a number of pixels. The essence of image feature extraction is to abstract and simplify the expression of complex image information. On this basis, various visual effects can be further completed. tasks such as image retrieval, image recognition, etc. [0003] The local features of the image are designed to express the invariant information of the essence of the local object area in the image. This feature does not change due to the change of the shape of the object in the image. At the same time, there are essential differences in the characteristics of different objects, just like whether people No matter how the shape changes, its genes always remain the same, and even if two people have similar appearances,...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method for extracting local features of images to solve the problems of large amount of computation and low efficiency when using Siamese networks for feature extraction; meanwhile, it also provides a device for extracting local features of images, currently using Siamese networks for feature extraction The problem of large amount of computation and low efficiency when extracting

Images