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

Multi-instance weighted packet learning method for online uncertain image recognition

An image recognition and learning method technology, applied in the field of online image recognition, can solve problems such as inability to effectively express and learn, reduce image recognition accuracy, and uncertain image data.

Active Publication Date: 2015-11-18
SHENZHEN TISMART TECH CO LTD
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a kind of online uncertain image recognition oriented multi-level solution to solve the problem that the single-example-based technology cannot effectively express and learn it, thereby reducing the accuracy of image recognition. Example weighted bag learning method

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
  • Multi-instance weighted packet learning method for online uncertain image recognition
  • Multi-instance weighted packet learning method for online uncertain image recognition
  • Multi-instance weighted packet learning method for online uncertain image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will now be described in detail in conjunction with the accompanying drawings.

[0031] Refer to attached figure 1 , a multi-instance weighted bag learning method for online uncertain image recognition, including the following steps,

[0032] (1) Obtain an image frame and perform feature extraction;

[0033] (2) Select an image from the data set to label, and determine a representative example of the label;

[0034] (3) In the case of noise in the package examples, different weights are given to the examples in the package to reduce noise, iteratively train the classifier, train the example weights, improve the package representation, reduce the impact of noise on the classification results, and improve the classification accuracy.

[0035] (4) Obtain a multi-instance classifier to classify and recognize images.

[0036] Existing multi-instance methods for image data assume that there is no noise in the packet. Today's real-world data is extrem...

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 provides a multi-instance weighted packet learning method for online uncertain image recognition, which reduces the influence of noise data on classification results in online image recognition through improving a multi-instance learning algorithm, and puts forward the ideal of endowing different weights to packet instances, updating a classifier continuously and adjusting the weights to increase classification accuracy. The multi-instance weighted packet learning method is different from the traditional multi-instance learning method for image recognition in that: during the traditional multi-instance learning, a training set is composed of a plurality of packets, each packet comprises a plurality of instances, and tags of the packet instances are unknown. The multi-instance weighted packet learning method for online uncertain image recognition reduces the interference of noise instances on classification prediction through weighing the instances, iterates the training classifier, trains instance weights, represents the packets and achieves higher classification accuracy.

Description

technical field [0001] The invention relates to the technical field of online image recognition, in particular to an image recognition technology based on multiple examples. Background technique [0002] With the rapid development of the Internet of Things+, online image recognition, such as face recognition, has been widely used. In this application process, due to the influence of online shooting equipment, data transmission, shooting scenes and other factors, the images obtained online often contain noise or uncertain data, which seriously affects the application of online image recognition technology. Therefore, it is of certain research significance to study the multi-instance weighted bag learning method for online uncertain image recognition. [0003] Existing multi-instance methods for image data assume that there is no noise in the packet. Today's real-world data is extremely susceptible to noise. In reality, due to uncertain factors such as the environment for o...

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): G06K9/62
CPCG06F18/2411
Inventor 肖燕珊刘波郝志峰张丽阳阮奕邦李杰龙
Owner SHENZHEN TISMART TECH CO LTD
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