Related feedback method for actively selecting multi-instance multi-mark digital image

A digital image and related feedback technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as limited information and inability to adapt to automatic image labeling

Active Publication Date: 2016-10-12
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The information obtained by this feedback method is very limited, and it cannot be adapted to the problem of automatic image annotation under multi-instance multi-label representation.

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
  • Related feedback method for actively selecting multi-instance multi-mark digital image
  • Related feedback method for actively selecting multi-instance multi-mark digital image
  • Related feedback method for actively selecting multi-instance multi-mark digital image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] Such as figure 1 Shown is the working flow diagram of the digital image automatic labeling device. Assume that the training image data set consists of two parts, one part has been marked, assuming a total of N 1 images, denoted by L; the other part is unmarked and fed back by users, assuming that there are N 2 image, denoted by U. The device extracts the images in the data set according to the characteristics of the multi-instance multi-label learning input. Each image is represented by a set of feature vectors, and each feature vector is called an example. Feature extraction can use the classic methods in machine learning textbooks to generate applicable image features, such as image segmentation first, and then extracting features such as color, texture, and shape for each image block. First, according to the feature vector of the image in L (assuming X L Represented) and the related information between the image and the mark (assuming Y L , when the value is 1, ...

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 related feedback method for actively selecting a multi-instance multi-mark digital image. Multi-instance multi-marking learning is a new machine learning frame which is presented in recent years and is successively applied in many practical problems. Image automatic marking technology based on multi-instance multi-mark input expression can be well applied on real tasks. But along with expression capability improvement, demand of marked training samples rapidly increases along with expression space increase. According to the related feedback method, through combining multi-instance multi-mark learning and active studying technology in machine learning, under a precondition that user marking cost does not increase, more fine and abundant marking information is obtained in a process of each related feedback, thereby improving system marking precision to a higher extent, and effectively reducing participation cost of the user.

Description

technical field [0001] The invention belongs to the technical field of digital image automatic labeling, and in particular relates to a correlation feedback method for actively selecting multi-instance and multi-label digital images. Background technique [0002] With the popularity of digital products and the popularity of various social networking sites, digital images have become the carrier of more and more Internet content. In order to efficiently utilize these digital image data, one of the core and most difficult tasks is to let the computer understand the semantics of the image, and automatic image annotation is the key technology. Current automatic image annotation techniques tend to represent images as single examples and only focus on the relevance of images to a single semantic category. However, images often have complex semantics and contain multiple object entities, so the representation of a single instance and a single label will cause information loss, and...

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): G06K9/62
CPCG06F18/2155G06F18/2178
Inventor 黄圣君高能能
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap