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

Sensitive image identification method based on depth learning

A sensitive image and deep learning technology, applied in the field of sensitive image recognition based on deep learning, can solve the time-consuming and labor-intensive problems of manual recognition of sensitive images, and achieve the effect of enhancing learning ability and simple method

Inactive Publication Date: 2017-05-17
FUDAN UNIV
View PDF15 Cites 42 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the time-consuming and labor-intensive shortcomings of manual identification of sensitive images, and provide a method based on deep learning to improve the efficiency of sensitive image identification

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
  • Sensitive image identification method based on depth learning
  • Sensitive image identification method based on depth learning
  • Sensitive image identification method based on depth learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The technical scheme of the present invention will be further described below.

[0051] 1. Extract sensitive image information from the collected sensitive image database, mainly to cut out the part containing sensitive information in the sensitive image and reduce the influence of the noise part.

[0052] 2. Perform preprocessing operations on sensitive image information before training, mainly converting the image into a jpg format image, scaling the image to a size of 256*256, and finally generating an image path / label(0,1,2...m) formatted text.

[0053] 3. Divide all preprocessed sensitive images into training set and test set, that is, divide all images into training set and test set according to the ratio of training set:test set is about 10:1

[0054] 4. Use the training set for deep neural network (DNN) training, and start training the model using the training interface provided by the deep learning open source framework caffe.

[0055] 5. Sensitive image test...

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 belongs to the technical field of digital image processing, and particularly relates to a sensitive image identification method based on depth learning. The method mainly comprises following steps of preprocessing sensitive images; dividing all preprocessed sensitive image databases into a training set and a test set, wherein the training set is divided into a train part and a validation part with proportion of 5:1, and using the images of the training set in a depth convolution neural network training, wherein parameters between layers of the convolution neural network are obtained through the training; after the training is finished, using a trained model to initializing a test neural network, wherein the test neural network is the same as a trained grid in structure; and inputting test sensitive images into the initialized depth neural network for identification test, thereby achieving identification of the sensitive images. According to the invention, functions of extraction and classification of features can be finished without manual participation and adjustment, and the reliable sensitive image identification method with high performance is provided.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, and in particular relates to a sensitive image recognition method based on deep learning. Background technique [0002] With the rapid popularization of the Internet, especially the mobile Internet, multimedia data represented by images and videos is growing at an alarming rate. How to detect sensitive images in Internet content has become a research hotspot. Sensitive images mainly refer to: pornography, violence, reactionary, sensitive figures (such as Dalai Lama), etc. Traditional monitoring methods mainly rely on manpower. With the explosive growth of multimedia content, manual inspection can no longer meet actual needs. On the one hand, data such as video images are growing explosively, and manual methods cannot undertake a huge verification workload; on the other hand, there are a large amount of outdated or verified data, resulting in a large amount of useless repetitive ...

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): G06K9/62G06K9/46G06K9/66G06N3/08G06N3/04
CPCG06N3/084G06V10/40G06V30/194G06N3/045G06F18/214
Inventor 胡二雷杜姗姗冯瑞金城薛向阳
Owner FUDAN UNIV
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