Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image feature extraction method and device

An image feature extraction and feature map technology, which is applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of increasing small target information and limited improvement, so as to increase diversity, improve performance and application range wide effect

Inactive Publication Date: 2019-07-05
CENT SOUTH UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the methods for detecting small targets can be roughly divided into two categories. One is to enlarge the target by enlarging the image, thereby increasing the information of the small target. This type of method brings limited improvement; the other is to use or integrate convolutional neural networks. The multi-layer feature map in the multi-layer feature map to obtain sufficient small target feature information, but these methods have not dealt with the noise in the map

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 feature extraction method and device
  • Image feature extraction method and device
  • Image feature extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The present invention will be further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the protection scope of the present invention is not limited thereby.

[0026] The image feature extraction method of this embodiment includes: S1. Generate an initial feature map based on the convolutional neural network and the target image to be detected. S2. Input the initial feature map into the initial module to further learn high-level abstract feature information to obtain an enhanced feature map. S3. Based on the enhanced feature map, use supervised learning to generate a length, width and enhanced feature Figure 1 feature saliency map. S4. Normalize the feature saliency map. S5. Multiply the initial feature map and the normalized feature saliency map to obtain a purified feature map.

[0027] Such as figure 2 As shown, this example shows that the ability of Faster RCNN to detect small targets is optimized in combinati...

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 feature extraction method and device, and the method comprises the steps: S1, generating an initial feature map based on a convolutional neural network and a to-be-detected target image; S2, inputting the initial feature map into an initial module to further learn high-order abstract feature information to obtain an enhanced feature map; and S3, based on the enhanced feature map, generating a feature saliency map with the same length and width as the enhanced feature map by using supervised learning; and S4, performing normalization processing on the feature saliency map; and S5, multiplying the initial feature map by the normalized feature saliency map to obtain a purified feature map. The noise in the feature map can be inhibited, the target information is highlighted, and the small target detection capability of the model is improved.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to an image feature extraction method and device. Background technique [0002] After the convolutional neural network was introduced into the field of target detection, the machine's ability to recognize image targets has been greatly improved, and it has also attracted many scholars to participate in the research in this field. Small object detection has always been a challenging and hot research topic in the field of image detection. The difficulty of small target detection is mainly due to the lack of object feature information and sensitivity to noise. At present, the methods for detecting small targets can be roughly divided into two categories. One is to enlarge the target by enlarging the image, thereby increasing the information of the small target. This type of method brings limited improvement; the other is to use or integrate convolutional neural networks. The multi-layer...

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
IPC IPC(8): G06K9/32G06K9/46G06N3/04
CPCG06V10/25G06V10/44G06N3/045
Inventor 刘青青杨学李建彬
Owner CENT SOUTH UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com