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

Small sample image feature enhancement method and system, image classification method and system

A technology of image features and small samples, which is applied in image enhancement, graphic image conversion, image data processing, etc., can solve the problem of small sample image classification accuracy decline, and achieve the effect of improving classification accuracy

Active Publication Date: 2021-07-02
南京智莲森信息技术有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a small-sample image feature enhancement method and system, an image classification method and system, and solves the problem that the accuracy of small-sample image classification decreases

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
  • Small sample image feature enhancement method and system, image classification method and system
  • Small sample image feature enhancement method and system, image classification method and system
  • Small sample image feature enhancement method and system, image classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be further described below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solution of the present invention more clearly, but not to limit the protection scope of the present invention.

[0034] A small-sample image feature enhancement method, comprising the following steps:

[0035] Step 1: Perform multiple affine transformations on the image to be enhanced to obtain multiple feature images of the image to be enhanced.

[0036] Here, a multi-level space transformation network is used to perform affine transformation on the image to be enhanced, that is, a space transformation is performed, and a different multi-level space transformation network is used each time.

[0037] The multi-level spatial transformation network is: replace the convolutional layer in the original spatial transformation network with a cascaded form of multiple convolutional layers, and the scale of the mu...

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 a small-sample image feature enhancement method and system, and an image classification method and system. The invention performs multiple affine transformations on the image to generate multiple feature images of the original image, and utilizes the similarity between the feature images to Feature enhancement is performed on key feature images to improve the classification accuracy of small sample images.

Description

technical field [0001] The invention relates to a small-sample image feature enhancement method and system, an image classification method and system, and belongs to the field of image classification. Background technique [0002] In recent years, computer vision has been widely used in various fields, liberating social productivity. Image classification is a very important task in computer vision. [0003] The traditional image classification method is mainly divided into two steps: feature extraction and classifier training; in the feature extraction stage, researchers use general features such as HOG, and design special features for different tasks. In practical tasks, researchers select an appropriate feature extraction algorithm based on computational complexity and accuracy requirements, and then use traditional machine learning algorithms such as Naive Bayesian, Random Forest, and Support Vector Machines to train a classification model. The implementation process of ...

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 Patents(China)
IPC IPC(8): G06T3/00G06T5/00G06K9/62G06N3/08
CPCG06T5/00G06N3/08G06F18/24G06T3/02
Inventor 吴泽彬徐洋邓伟诗龚航詹天明郑鹏
Owner 南京智莲森信息技术有限公司