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

Image content identification method and device and terminal

An image content and recognition method technology, applied in the field of image recognition, can solve the problem of inability to take into account the recall rate, and achieve the effect of reducing the number of sample images, ensuring the accuracy rate, and increasing the recall rate

Active Publication Date: 2018-07-06
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF1 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide an image content recognition method, device, and terminal to solve the problem in the prior art that the accuracy rate of recognition results of convolutional neural networks and the recall rate of samples cannot be balanced

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 content identification method and device and terminal
  • Image content identification method and device and terminal
  • Image content identification method and device and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] refer to figure 1 , shows a flow chart of steps of an image content recognition method according to Embodiment 1 of the present invention.

[0034] The image content recognition method of the embodiment of the present invention may include the following steps:

[0035] Step 101: In the process of training the convolutional neural network, input sample images into the convolutional neural network.

[0036] Among them, the sample images are used for iterative training of the convolutional neural network.

[0037] The convolutional neural network in the embodiment of the present invention can be a multi-category content recognition model, which can identify the category to which an image belongs; it can also be a binary content recognition model, which can identify whether an image belongs to a certain category. After the convolutional neural network modeling is completed, it needs to use a large number of sample images for multiple iterations of training to ensure the c...

Embodiment 2

[0052] refer to figure 2 , shows a flow chart of the steps of the image content recognition method according to Embodiment 2 of the present invention.

[0053] The image content recognition method in the embodiment of the present invention may specifically include the following steps:

[0054] Step 201: In the process of training the convolutional neural network, input sample images into the convolutional neural network.

[0055] Among them, the sample images are used for iterative training of the convolutional neural network. After the convolutional neural network modeling is completed, it needs to use a large number of sample images for multiple iterations of training to ensure the convergence of the convolutional neural network and ensure the accuracy of the prediction results. The specific process of training the convolutional neural network through the sample image each time is the same. In the embodiment of the present invention, an iterative training of the convoluti...

Embodiment 3

[0084] refer to image 3 , shows a structural block diagram of an image content recognition device according to Embodiment 3 of the present invention.

[0085] The icon content recognition device in the embodiment of the present invention may include: an input module 301 configured to input a sample image into the convolutional neural network during the training process of the convolutional neural network, wherein the sample image is used for The convolutional neural network performs iterative training; the determination module 302 is configured to determine the number of trained iterations of the convolutional neural network; the loss function adjustment module 303 is configured to adjust the loss based on the number of trained iterations The function obtains the target loss function; the training module 304 is configured to perform this iterative training according to the target loss function to obtain the target convolutional neural network; the prediction module 305 is con...

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 embodiment of the invention provides an image content identification method and device and a terminal. The method includes: inputting sample images to a convolutional neural network in a process of training the convolutional neural network, wherein the sample images are used for iteratively training the convolutional neural network; determining the number of already passed training iterationsof the convolutional neural network; adjusting a loss function on the basis of the number of the already passed training iterations to obtain a target loss function; carrying out iterative training according to the target loss function to obtain a target convolutional-neural-network; and carrying out content identification on a to-be-identified image through the target convolutional-neural-network. Through the convolutional-neural-network training scheme provided by the embodiment of the invention, distribution of the complex image samples can be better fitted, the number of sample images of intermediate probability value distribution can be decreased, and thus a recall rate of samples can be increased in a case of ensuring an identification result accuracy rate of the convolutional neuralnetwork.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to an image content recognition method, device and terminal. Background technique [0002] Deep learning has been widely used in video images, speech recognition, natural language processing and other related fields. As an important branch of deep learning, convolutional neural network has greatly improved the accuracy of prediction results obtained in computer vision tasks such as target detection and classification due to its strong fitting ability and end-to-end global optimization ability. [0003] However, in practical applications, the results generated by convolutional neural networks are generally not directly used. Taking a binary classification task as an example, for an input data convolutional neural network, it will give its probability in a certain category. The probability threshold will be set according to the specific application scenario. Usuall...

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
CPCG06F18/214
Inventor 张志伟杨帆
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
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