Image detection method and device

An image detection and image technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of few application fields of image recognition technology, low recognition accuracy and speed, and achieve enhanced network security and improved efficiency , the effect of saving labor costs

Inactive Publication Date: 2018-11-13
上海东方报业有限公司
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to overcome the disadvantages of less application fields, lower recognition accuracy and lower

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
  • Image detection method and device
  • Image detection method and device
  • Image detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] This embodiment provides an image detection device, and the image detection device includes three databases, namely a pornographic database, a politically sensitive database, and a violent terror database.

[0048] Among them, the data stored in the pornographic database is used to identify pornographic images, the politically sensitive database includes the avatars or text of political leaders, which is used to identify politically sensitive images, and the data stored in the violent and terrorist database is used to identify images that record terrorism and violent incidents .

[0049] see figure 1 , using the image detection device, this embodiment provides an image detection method, including:

[0050] Step 100, acquiring the image to be tested of the user avatar uploaded by the user.

[0051] The image to be tested is used as an image used as a user avatar after registration.

[0052] Step 101, identifying feature points in the image to be tested;

[0053] Step...

Embodiment 2

[0061] see figure 2 , this embodiment is basically the same as Embodiment 1, the only difference is:

[0062] Step 200, acquiring the image to be tested of the user avatar uploaded by the user.

[0063] Step 201. Identify the feature points of the skin in the image to be tested.

[0064] Step 202. Determine whether the ratio of the skin area in the image to be tested to the area of ​​the image to be tested is greater than a second preset value according to the feature points of the skin. If yes, execute step 203; otherwise, execute step 204.

[0065] Step 203, setting the pornography-related database as a target database, and then performing step 205.

[0066] Step 204. Determine whether the ratio of the skin area in the image to be tested to the area of ​​the image to be tested is less than a third preset value, and if so, set the politically sensitive database and the violent terror database as target databases.

[0067] Step 205, comparing the feature points in the targ...

Embodiment 3

[0072] see image 3 , this embodiment is basically the same as Embodiment 1, the only difference is:

[0073] Step 104 is: judging whether the similarity value of the image to be tested is greater than a first preset value, if yes, execute step 105, otherwise, execute step 306.

[0074] Step 105, perform a preset operation, and then end the process.

[0075] Step 306, acquiring the image of the reported user's avatar.

[0076] For the illegal pictures that pass the detection, this application can also receive reports.

[0077] Step 307, comparing the feature points of the reported image with the latest target database;

[0078] Step 308, determine whether the reported image is legal, if so, execute step 309, otherwise execute step 310,

[0079] Step 309 : Manually detect the reported images and manually add the reported images marked as illegal to the target database, and then end the process.

[0080] Step 310, adding the reported image to the target database.

[0081] Th...

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 an image detection method and device. The image detection device comprises a plurality of databases. The image detection method comprises the steps that a to-be-detected imageof a user icon uploaded by a user is acquired; feature points in the to-be-detected image are recognized; the feature points are compared in a target database, wherein the target database is one of the plurality of databases; a similar value of the to-be-detected image and an image in the target database is acquired; and when the similar value of the to-be-detected image is greater than a first preset value, preset operation is executed. Through the image detection method and device, whether the icon uploaded by the user is legal can be judged quickly and timely, so that manpower cost is saved, efficiency is improved, and network security is enhanced; and furthermore, quick recognition can be realized, and recognition accuracy is higher.

Description

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

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
Owner 上海东方报业有限公司
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