Image retrieval sorting method based on rapid geometric consistency verification
A retrieval sorting and consistency technology, applied in digital data information retrieval, instruments, biological neural network models, etc., can solve the problems of low image reordering efficiency and low image retrieval efficiency.
Pending Publication Date: 2022-05-31
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide an image retrieval and sorting method based on fast geometric consistency verification to solve the problem of low image retrieval efficiency caused by low image reordering efficiency in the prior art
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
[0026] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.
[0027] The present invention proposes an image retrieval and sorting method based on fast geometric consistency verification. The specific process of the method is as follows: figure 1 shown. The present invention firstly searches based on the features of the query image and the reference image, obtains the candidate reference image and the initial sorting result according to the retrieval result, and generates a matching point pair between the query image and the candidate reference image; The candidate benchmark images are subjected to geometric consistency verification to realize the reordering of the candidate benchmark images.
[0028] Step 1. Obtain data and feature extraction
[0029] The present invention first acquires the query image and the image database, and each image in the database has a corresponding unique descriptor (eg, n...
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 invention provides an image retrieval sorting method based on rapid geometric consistency verification, and belongs to the technical field of image retrieval. The method comprises the following steps: firstly, performing retrieval based on query image features and reference image features, obtaining candidate reference images and an initial sorting result according to a retrieval result, and generating matching point pairs of the query image and the candidate reference images; and performing geometric consistency verification on the query image and the candidate reference image according to the obtained matching point pair to realize reordering of the candidate reference image. When geometric consistency verification is carried out, the feature points of the candidate images and the query images do not need to be re-extracted, verification is carried out by directly using the generated matching point pairs of the query images and the candidate reference images, the existing geometric consistency verification efficiency is improved, and meanwhile, the re-ordering efficiency of the candidate images is also improved; compared with other reordering methods, the method does not need sample learning, and also improves the reordering speed of the candidate images.
Description
technical field [0001] The invention relates to an image retrieval and sorting method based on fast geometric consistency verification, and belongs to the technical field of image retrieval. Background technique [0002] With the development of imaging technology, the amount of remote sensing image data continues to increase. These remote sensing images can provide good data support for different fields (environmental monitoring, disaster warning, urban development, etc.) It is a problem that needs to be solved urgently. The existing methods all retrieve the target related images from the database first, and then reorder the retrieved related images. The image retrieval reordering is to use the content information of the images to rearrange the images in the initial query result, so that the final image is reordered. The query results can better meet the needs of users. [0003] In the paper titled "Retrieval of Remote Sensing Image Content Based on Image Learning Represen...
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 Applications(China)
IPC IPC(8): G06F16/535G06F16/538G06F16/583G06N3/04
CPCG06F16/535G06F16/538G06F16/583G06N3/045
Inventor 蓝朝桢秦剑琪周扬施群山张衡邢帅吕亮李鹏程胡校飞
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU