Image retrieval method, device, electronic device and storage medium
An image retrieval and image technology, applied in the computer field, can solve problems such as insufficient images, recall, and inaccurate retrieval results
Active Publication Date: 2022-02-25
TENCENT TECH (SHENZHEN) CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, using the above image retrieval method, only images similar to the basic feature embedding can be recalled, and some images similar to other features of the query image cannot be recalled through the basic feature embedding, which leads to insufficient recalled images, making the retrieval results inaccurate
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0088] In order to make the purpose, technical solution and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0089] In order to facilitate those skilled in the art to better understand the technical solution of the present application, some concepts involved in the present application are introduced below.
[0090] embedding: It is the feature extracted from the original data, that is, the low-dimensional vector after mapping through the neural network. Image embedding is a process of mapping graph data (usually a high-dimensional dense matrix) into a low-density vector. Gra...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application provides an image retrieval method, device, electronic equipment, and storage medium, which relate to the field of computer technology and can be applied to various scenarios such as cloud technology, artificial intelligence, intelligent transportation, and assisted driving. The method includes: based on the target basic features of the query image, recalling a first set of images having similar basic features to the query image; based on the target semantic features of the query image, selecting a plurality of images from the first set of images having similar semantic features to the query image Candidate images; based on the respective semantic features of the multiple candidate images, recalling a second image set having similar semantic features to the corresponding candidate images; based on the recalled multiple second image sets and the first image set, determining the retrieved target image gather. This application adopts a two-level recall method, which can increase the retrieval recall rate and further improve the accuracy of retrieval results.
Description
technical field [0001] The present application relates to the field of computer technology, and in particular to an image retrieval method, device, electronic equipment and storage medium. Background technique [0002] With the rapid development of deep learning technology, image retrieval technology based on deep learning technology has been widely used. At present, for the image library to be retrieved, the image feature extraction model based on metric learning training in deep learning is used to extract the basic feature embeddings of each image in the image library, and represent the corresponding image through the basic feature embedding. [0003] When it is necessary to retrieve similar images of the query image from the image database, the image feature extraction model is used to extract the basic feature embedding of the query image, and then the basic feature embedding of the query image is calculated with the basic feature embedding of each image in the image da...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/583
CPCG06F16/583
Inventor 郭卉
Owner TENCENT TECH (SHENZHEN) CO LTD