Movable terminal porn filtering method based on analyzing image and semantics

A semantic analysis and image technology, applied in the field of image processing, can solve problems such as undetectable

Active Publication Date: 2013-05-08
BEIJING UNIV OF TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, a lot of work has been done in the research of content-based sensitive image filtering at home and abroad, which can solve the problem that some pornographic websites cannot be detected because of deliberately jumping IP and changing domain names, but the processing speed and processing accuracy are still at this level. a bottleneck in the way

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
  • Movable terminal porn filtering method based on analyzing image and semantics
  • Movable terminal porn filtering method based on analyzing image and semantics
  • Movable terminal porn filtering method based on analyzing image and semantics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The present invention will be further described below in conjunction with the accompanying drawings.

[0060] Such as figure 1 As shown, the sensitive area detection method based on image semantic analysis includes the following steps:

[0061] Step 1, input training images.

[0062] Step 2, extract the features of the input training image, such as figure 2 As shown, the method of extracting the features of the input training image is as follows:

[0063] ① Segment image blocks and calculate the dissimilarity between image blocks;

[0064] ②Calculate the dissimilarity between each image block and all other image blocks, and establish a saliency map;

[0065] ③Establish sensitive area correlation map;

[0066] ④ The weighted dot product of the saliency map and the correlation map of sensitive parts is obtained to obtain the attention guidance map;

[0067] ⑤ Take the sensitive part as the current salient area according to the attention guidance map;

[0068] ⑥ Se...

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 movable terminal porn filtering method based on analyzing image and semantics. The movable terminal porn filtering method based on analyzing image and semantics realizes of adding self top downward visual attention mechanism and reinforcing performance and effect of classifier practice in the pre-processing stage of the practice classifier, and classifies the image by the well-practiced classifier. The movable terminal porn filtering method comprises the following steps: inputting the practice image; extracting the features of the practice image; practicing plurality of weak classifiers through the features extracted, and forming the final strong classifier in parallel connection; inputting test image and pre-processing the test image, and demarcating a possible location of a sensitive area in the image through the visual attention mechanism; testing the sensitive image; and finally outputting the testing result of the sensitive image. A striking image extraction of the self top downward visual attention mechanism is started before testing the sensitive image, so that the method can improve the calculation efficiency, shorten calculation time, strikingly improve testing speed; and therefore a positive test rate is effectively improved and an error rate is effectively lowered.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a mobile terminal pornography filtering method based on image semantic analysis. Background technique [0002] The China Internet Network Information Center released the "2011 Survey Report on Internet Behavior of Chinese Youth". Level 26.1 percentage points. In 2011, there were 19.36 million new young netizens, a year-on-year increase of 9.0%. It is particularly worth mentioning that from 2007 to 2010, the proportion of teenagers surfing the Internet by mobile phone has increased from 49.7% to 80.3%. With the rapid development of the mobile Internet, especially the development of 3G networks and the development of mobile terminals such as smart phones and tablet computers, the proportion of minors using mobile phones to surf the Internet will further increase. Before December 2009, the relevant research group of the Chinese Academy of Sciences also randomly sampled...

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
Inventor 段立娟谷继力吴春鹏杨震苗军李健马伟乔海涛张祺
Owner BEIJING UNIV OF TECH
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