Method for filtering internet hemp image

A filtering method and Internet technology, applied in the field of computer network security, can solve the problems of large amount of calculation, no point of interest positioning and scale invariance, etc., and achieve the effect of broad application prospects

Active Publication Date: 2012-06-27
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the disadvantage is that the recognition is similar to exhaustive search, there is no interest point positioning and scale-invariant properties, and the amount of calculation is very large

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
  • Method for filtering internet hemp image
  • Method for filtering internet hemp image
  • Method for filtering internet hemp image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] Various details involved in the technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be pointed out that the described embodiments are only intended to facilitate the understanding of the present invention, rather than limiting it in any way.

[0041] Main features of the present invention are:

[0042] 1) The construction of self-similar weak classifiers, these self-similar weak classifiers should complement each other as much as possible to provide classification information to the greatest extent. For the recognition and filtering of marijuana images, the self-similarity weak classifier should be able to capture the characteristics of such objects well, that is, the self-similarity of the internal structure of the object.

[0043] see figure 1 For a schematic illustration of an example of a cannabis image on the Internet in the prior art, see also Figure 7 , which is a schematic dia...

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 a method for filtering an internet hemp image. The method comprises the following steps of: extracting local features of an image by using a dimension invariant feature transformation algorithm; establishing a self-similarity weak classifier for each local feature of each hemp training image; observing if any tested image is similar to the hemp image having the local features of the self-similarity weak classifiers and if the self-similarity is sufficient or not by the self-similarity weak classifiers; establishing a strong classifier by integrating the self-similarity weak classifiers if one tested image is similar to the hemp image having the local features of the self-similarity weak classifiers and has a sufficient self-similarity; and judging whether the image is the hemp image or not according to all local features of the image. The method of the invention uses the self-similarity weak classifiers and overcomes the shortcoming that the interior similarity relationship of the images cannot be considered in the identification method of the prior art so the features of the hemp image are efficiently captured.

Description

technical field [0001] The invention relates to the field of computer network security, in particular to a method for filtering Internet sensitive information. Background technique [0002] With the rapid development of the Internet, drug information, especially marijuana sales information, spreads rapidly on the Internet. Many illegal websites sell marijuana in the form of online shopping, and at the same time promote the theory that marijuana is harmless, causing greater harm to society. So, like filtering Internet pornography, filtering information about drugs, especially marijuana, has become a top priority. [0003] Beginning on January 1, 2001, the European Commission launched a project called "Network Protection (NetProtect, NetProtect II)" to develop an Internet multilingual filtering system. Its collected webpage database includes pornography, violence, bomb making and drugs. There are 4 categories in total, and researchers have tried various methods in the field ...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62H04L29/06
Inventor 胡卫明谢年华吴偶
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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