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

Image feature extraction method and device

An image feature extraction and image feature technology, applied in the field of image processing, can solve the problems of poor image feature accuracy and poor image quality.

Active Publication Date: 2021-06-22
上海皓桦科技股份有限公司
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of using this method is that not all images obtained by random transformation are reasonable, and some images obtained by random transformation are of poor quality, for example, the core part of some images will be cut off by using the method of random cropping , obviously, the accuracy of image features extracted by using these images for image feature learning is poor

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 1

[0064] See attached figure 2 , figure 2 It exemplarily shows a schematic diagram of performing model training on the image feature extraction model based on the image samples in the training set in this embodiment. In this embodiment, the image quality assessment model includes an image stitching module and a convolutional neural network; the image stitching module is configured to perform image stitching on each image sample and each randomly transformed image corresponding to each image sample, so as to obtain each Multiple spliced ​​images corresponding to image samples; the convolutional neural network is configured to obtain the image feature vector of the spliced ​​image, and perform image classification prediction according to the image feature vector, so as to obtain the random transformation image in the spliced ​​image and be predicted to be consistent with the spliced ​​image The probability that the image samples belong to the same category of images.

[0065] ...

Embodiment 2

[0069] See attached image 3 , image 3 It exemplarily shows a schematic diagram of performing model training on the image feature extraction model based on the image samples in the training set in this embodiment. In this embodiment, the image quality assessment model includes a feature extraction module and an image classification module, the module structure of the feature extraction module is the same as that of the image feature extraction model, and the image classification module includes a sequentially connected fully connected layer and a Sigmoid function layer The feature extraction module is configured to extract the image sample feature vector of each image sample and directly obtain the transformed image feature vector of each randomly transformed image extracted by the image feature extraction model when the image feature extraction model is model trained, and to The image sample feature vector of each image sample and the transformed image feature vector of eac...

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 relates to the technical field of image learning, particularly provides an image feature extraction method and device, and aims to solve the technical problem of how to improve the image feature learning effect. For this purpose, according to the method of the embodiment of the invention, image random transformation can be performed on each image sample in a training set to obtain one or more random transformation images corresponding to each image sample; classifying each random transformation image to form a first image set and a second image set; obtaining a quality evaluation value of each random transformation image according to each image sample by adopting an image quality evaluation model; performing model training on an image feature extraction model according to the first image set, the second image set and the quality evaluation value of each random transformation image; and carrying out image feature extraction on the target image by using the trained image feature extraction model. Through the steps, the model image feature learning effect can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image feature extraction method and device. Background technique [0002] Image classification based on deep learning often requires a large amount of labeled data, but the cost of obtaining a large amount of labeled data is high or even impossible. How to learn important features in images without labeling data (unsupervised), and then for Subsequent calculations provide a good foundation with high scientific and practical value. [0003] Among the existing unsupervised image feature learning methods, the one with the highest accuracy in extracting image features is the contrast-based unsupervised image feature learning method, which mainly constrains the embedding vectors between images obtained by random transformation of the same image. ) are close, while the embedding vectors of different images are far away to achieve unsupervised image feature learning. Howev...

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): G06K9/62G06N3/04G06N3/08G06T3/40G06T7/11
CPCG06T7/11G06T3/4038G06N3/084G06T2200/32G06N3/045G06F18/211G06F18/214
Inventor 冯建兴
Owner 上海皓桦科技股份有限公司
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