Method for extracting image region of interest by combining bottom-up and top-down ways

Abstract

The invention provides a method for extracting an image region of interest by combining bottom-up and top-down ways. In the method, an interactive way is adopted, a user converts top-down information of observation tasks carried by the user into different weight values which are used for inputting the image bottom-layer features, an Itti-Koch model and a Stentiford model are combined, and the advantages of the two models are absorbed, thus the method for extracting region of interest combined with a user task and image visual stimulation is realized. Inquiry intention of the user and understanding on the image are converted into weights of a saliency map, namely the bottom-layer features are added corresponding weights to influence the solution of the saliency map, thus a gap between the inquiry intention of the user and the bottom-layer features of an image is reduced and the extracted region of interest is more consistent with the requirement of the user. The processing results of multiple images show that better result can be obtained by adopting the method to extract the region of interest for the user.

Description

technical field [0001] The invention belongs to the technical field of image retrieval and image recognition, and relates to a bottom-up and top-down image interest region extraction method. technical background [0002] In the traditional content-based image retrieval, only the underlying features of the image are extracted without considering the user's understanding of the image, so the retrieval results are not ideal. Existing research shows that when a user observes an image, the part that is most likely to attract the user's attention is often the part that the user is interested in, and is also a part that is more prominent compared with other surrounding parts in the image. The visual attention model is used to get the part of the image that is most likely to attract attention. At the same time, because the retrieval results of the image retrieval system are directly related to people's understanding of the image, different people have different opinions on the same ...

AI Technical Summary

Problems solved by technology

[0006] In the existing method of extracting the region of interest of the image, basically only the underlying features such as image color, brightness and direction are extracted, and the user's processing requirements for the image and the user's different understanding of the image are not considered. may not be ideal for a specific requirement

Images