Image retrieval method and apparatus

Abstract

The invention discloses an image retrieval method and apparatus. The image retrieval method comprises the following steps of building a multi-task depth network structure model; establishing a target image feature library; inputting a feature subset of a to-be-retrieved image; calculating a similarity distance between the feature subset of the to-be-retrieved image and each image feature in the image feature library; and performing arrangement according to an arrangement order of distances from short to long to obtain an image with a minimum distance with the to-be-retrieved image. By building the depth network structure model for multi-task learning of the features of the target image, the image retrieval is finished; the precision of a plurality of attribute classifications can be jointly improved by fully utilizing a correlation of tasks; and a relationship of the attributes of the image and detail features of the image can be learnt, so that in the image retrieval process, the influence of climate, environment, illuminance and the like can be overcome.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image retrieval method and device. Background technique [0002] With the rapid development of computers and the Internet, multimedia image information is being rapidly generated and disseminated on the Internet, thereby enriching people's vision. Faced with various image information, mining the images that people need has become a concern. Therefore, the establishment of relevant image retrieval methods has become a hot spot in research and engineering practice. [0003] At present, the existing image retrieval methods generally use the deep learning of neural networks to directly apply a single attribute to complete the image retrieval of single-task learning features, because single-task learning features often only consider the amount of information of the task itself, and do not consider the relationship with other tasks. The connection between tasks, so the learning abil...

AI Technical Summary

Problems solved by technology

[0004] Therefore, the technical problem to be solved by the embodiments of the present invention is that the image retrieval method in the prior art completes the image retrieval of the single-task learning feature through a single attribute, and cannot learn the relationship between the various attributes of the image and the detailed features of the image. In the process, it is impossible to overcome the influence of climate, environment, and illumination, resulting in the slowdown of image retrieval progress and poor image retrieval effect

Images