Image compression method and device, server and storage medium
An image compression and image technology, applied in the field of image recognition, can solve the problem of not being able to have supervised training, and achieve the effect of improving retrieval quality
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0028] figure 1 It is a flow chart of the image compression method provided by Embodiment 1 of the present invention. This embodiment is applicable to the case of image compression. The method specifically includes the following steps:
[0029] S110. Extract a plurality of key points from the m sample images, and each key point includes a vector with a length of n.
[0030] In this embodiment, the representation of an image can be described by extracting key points of the image, which can also be called key point descriptors, including pixel feature vectors of the key points. In this embodiment, key points may be extracted by using a SIFT algorithm, that is, a scale-invariant feature transform (Scale-invariant feature transform, SIFT) algorithm. The algorithm takes the feature point as the center and takes a 16×16 neighborhood as the sampling window, and puts the relative direction between the sampling point and the feature point into a direction histogram containing 8 bins a...
Embodiment 2
[0043] figure 2 It is a flow chart of the image compression method provided by Embodiment 2 of the present invention. This embodiment is further optimized on the basis of the above-mentioned embodiments. The method specifically includes:
[0044] S210. Perform preprocessing on the m sample images to convert them into m grayscale images.
[0045] In this embodiment, if the sample image is a color image, the template image must first be converted into a grayscale image. Then adjust the resolution of the grayscale image obtained after conversion to 240x320, which can avoid generating a large number of SIFT key point descriptors, which can greatly reduce the matching time. Optionally, the preprocessing the m sample images to convert them into m grayscale images includes: performing denoising processing on the m sample images by using a median filter method; The m sample images are converted into m grayscale images by the RGB chromaticity space.
[0046] In this embodiment, the...
Embodiment 3
[0063] image 3 Shown is a schematic structural diagram of an image compression device 300 provided in Embodiment 3 of the present invention. This embodiment is applicable to image compression, and the specific structure is as follows:
[0064] A key point extraction module 310, configured to extract a plurality of key points for m sample images, each of which includes a vector with a length of n;
[0065] A clustering pixel matrix definition module 320, configured to cluster the key points to obtain multiple cluster centers, and use the multiple cluster centers to define a cluster pixel matrix;
[0066] An image clustering matrix generation module 330, configured to cluster the m sample images to which the key point belongs based on the distance between the key point and the centers of the multiple clusters, so as to obtain an image clustering matrix;
[0067] An image compression matrix generation module 340, configured to generate an image compression matrix according to t...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


