Unlock instant, AI-driven research and patent intelligence for your innovation.

Data processing method, device and readable storage medium based on neural network model

A neural network model and data processing device technology, applied in the field of image recognition, can solve the problems of low training quality and affect the accuracy of the recognition structure of gesture recognition, and achieve the effect of improving the training quality and the recognition accuracy.

Active Publication Date: 2019-01-01
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF10 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problem that the training quality of the existing neural network model is not high, which affects the accuracy of the recognition structure of gesture recognition, the application provides a data processing method, device and readable storage medium based on the neural network model

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
  • Data processing method, device and readable storage medium based on neural network model
  • Data processing method, device and readable storage medium based on neural network model
  • Data processing method, device and readable storage medium based on neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.

[0049] Gesture recognition is widely used in a large number of application fields. For example, in the field of smart home appliances, many smart devices can control their functions such as power on and off through gestures; in the field of monitoring, the gestures of the monitored objects can be recognized to obtain monitoring information, etc. The neural network has broad and attractive prospects in the fields of system identification, pattern recognition, intelligent control, etc., and it is also used in gesture recognition.

[0050] Before gesture recognition, it is necessary to effectively train the constructed neural network model, in which the quality o...

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 provides a data processing method based on a neural network model, a device and a readable storage medium, wherein, a neural network model to be trained for recognizing gestures is established; a training set is formed for training the neural network model based on the obtained image data including gesture information, wherein the training set comprises a plurality of training subsets divided according to training difficulty, each image data belonging to one of the training subsets; according to the training difficulty corresponding to each training subset, the neural network model to be trained is trained many times to obtain the trained neural network model for gesture recognition, thereby effectively improving the training quality of the neural network model and further improving the recognition accuracy of the gesture.

Description

technical field [0001] The invention relates to image recognition technology, in particular to a data processing method, device and readable storage medium based on a neural network model. Background technique [0002] Gesture recognition is widely used in a large number of application fields, for example, the field of smart home appliances, the field of monitoring and so on. The use of neural network models to recognize gestures has also become a hot technology. [0003] Generally speaking, before the recognition, the neural network model needs to be effectively trained, and the quality of the training data will affect the training results, thereby affecting the subsequent gesture recognition results. [0004] Therefore, how to improve the training quality of the neural network model for gesture recognition so that it can recognize gestures more accurately becomes a problem. Contents of the invention [0005] In view of the above-mentioned problem that the training qual...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/28G06V40/113G06F18/214
Inventor 杨少雄赵晨
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD