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

Network malicious image detection method based on visual word bag

A visual word bag and image detection technology, applied in the field of network information security, can solve the problems of low positive detection rate, high detection time cost, and high false detection rate

Inactive Publication Date: 2014-10-29
XIAN UNIV OF TECH
View PDF1 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a network bad image detection method based on visual bag of words, which solves the problems of low positive detection rate, high false detection rate and high detection time cost in the existing bad image detection 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
  • Network malicious image detection method based on visual word bag
  • Network malicious image detection method based on visual word bag
  • Network malicious image detection method based on visual word bag

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0048] The present invention is based on the network bad image detection method of bag of visual words, implements according to the following steps:

[0049] 1. Image preprocessing, used to obtain the skin color area in the image; 2. Feature extraction and description, to obtain the feature vector of the key points of the skin color area; 3. Construct a visual word bag, and extract the features that best represent the image features from the key points of the image The vectors are screened out to form the bag of visual words of the image; 4. Image detection, the trained classifier is used to classify the bag of visual words of the image, so as to complete the work of bad image detection.

[0050] The defective image detection model established by the present invention is mainly composed of four basic modules: a skin color area detection modul...

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 network malicious image detection method based on a visual word bag. The method is specifically implemented according to the following steps of: image pretreatment, including obtaining a skin color area in the image; feature extraction and description, including obtaining feature vectors of the key point in the skin color area; building a visual word bag, screening out the feature vector which can best represent the feature of the image from the image key point, and thereby constituting the visual word bag of the image; image detection, including classifying the visual word bag of the image by a trained classifier, and thereby completing the detection of the malicious image. When being used for identifying and detecting malicious images, compared with other similar method, the network malicious image detection method based on the visual word bag is higher in correct detection rate and shorter in detection time, can be used as an efficient network malicious image detection method, and has certain theoretical and practical values.

Description

technical field [0001] The invention belongs to the technical field of network information security, and relates to an image recognition and inspection method, in particular to a method for detecting bad network images based on a bag of visual words. Background technique [0002] The bag-of-words model was originally applied in the field of document detection and classification, and has been widely used because of its simplicity and effectiveness. For this reason, researchers in the field of computer vision have tried to apply the same method to the field of image processing and recognition. The bag model is a study of the transition from the field of text processing to the field of image processing. [0003] The research results show that the representation of image features by using the bag of visual words makes the image features have high stability and accuracy, which meets the requirements of image classification and detection, and can be used as an effective image dete...

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): G06K9/00G06K9/62G06K9/46
Inventor 吕林涛朱珊王锦辉
Owner XIAN UNIV OF TECH
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