Unlock instant, AI-driven research and patent intelligence for your innovation.

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

Active Publication Date: 2020-07-10
SOUTH UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, at present, the datasets of ophthalmic images are collected for classification, segmentation, and detection tasks. When these datasets are used for retrieval tasks, only supervised training of correlation labels can be performed, but supervised training of correlation levels cannot be performed.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image compression method and device, server and storage medium
  • Image compression method and device, server and storage medium
  • Image compression method and device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

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...

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

No PUM Login to View More

Abstract

The invention discloses an image compression method and device, a server and a storage medium, and the method comprises the steps: extracting a plurality of key points from m sample images, wherein each key point comprises a vector with the length of n; clustering the key points to obtain a plurality of clustering cluster centers, and defining a clustering pixel matrix by using the plurality of clustering cluster centers; clustering the m sample images to which the key points belong based on the distances between the key points and the centers of the plurality of clustering clusters to obtainan image clustering matrix; and generating an image compression matrix according to the clustering pixel matrix and the image clustering matrix so as to define m target images after m sample images are compressed, wherein each target image comprises a vector with the length of n. According to the technical scheme, image retrieval and correlation level labeling in retrieval are facilitated, so thatthe retrieval quality is improved.

Description

technical field [0001] Embodiments of the present invention relate to image recognition technology, and in particular to an image compression method, device, server and storage medium. Background technique [0002] With the development of imaging technology, ophthalmology digital images have become the main data of ophthalmology. This trend drives the construction of ophthalmology image retrieval system to assist doctors in clinical decision-making. In recent years, in the field of medical imaging, deep learning algorithms represented by deep convolutional networks (CNN) have achieved excellent performance in disease classification and lesion segmentation of ophthalmic images, and have surpassed traditional classification in terms of extracting texture, color, shape and other features. Machines such as Support Vector Machine (SVM) and Random Forest (RF) have accelerated the development of ophthalmic image retrieval systems. However, the current ophthalmic image datasets are...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/55
CPCG06F16/55Y02D10/00
Inventor 方建生刘江
Owner SOUTH UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA