Feature extraction method and device of a tile image, electronic equipment and storage medium

Abstract

The invention provides a feature extraction method and device of a tile image, electronic equipment and a storage medium. The method comprises: obtaining a tile image set; calculating hash codes of the tile images in the tile image set through a perceptual hash algorithm; selecting a reference tile image from the tile image set; determining a first similarity of the to-be-detected tile image according to a size relationship between the hash code of the reference tile image and the hash code of the to-be-detected tile image; enabling the to-be-detected tile image to be a tile image in the tile image set except the reference tile image; respectively calculating a second similarity of the to-be-detected tile image relative to the reference tile image through a histogram similarity algorithm; and based on the first similarity and the second similarity, in combination with a similarity value calculation formula, obtaining a target similarity of the to-be-detected tile image. Therefore, the similarity between the to-be-measured tile image and the reference tile image is accurately determined, and the landform type and the proportion of the landform type included in the to-be-measured tile image are determined.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to a feature extraction method, device, electronic equipment and storage medium of a tile image. Background technique [0002] With the rapid development of multimedia technology and Internet technology, the phenomenon of using images as information carriers to communicate at work has become more and more common, so the management efficiency of image resources has been paid more and more attention. Traditional image resource management methods generally use Manually mark and index images to achieve the purpose of image resource management. [0003] Furthermore, for tile image resources, although traditional image resource management methods can extract all terrain types in the tile image, they cannot determine the proportion of various existing terrain and landforms. The proportion of different topography is the basis for determining the bird damage risk level and fire ...

AI Technical Summary

Problems solved by technology

[0003] Furthermore, for tile image resources, although traditional image resource management methods can extract all terrain types in the tile map, they cannot determine the proportion of various existing terrain and landforms.

Images