Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Chinese gesture language recognition method based on convolutional neural network

A convolutional neural network and recognition method technology, applied in biological neural network models, neural architecture, character and pattern recognition, etc., can solve the problems of expensive wearable devices and inconvenient use.

Inactive Publication Date: 2018-02-27
TIANJIN UNIV
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, gesture recognition methods are mainly divided into two categories. One is the method based on wearable devices. Although the real-time performance is better, wearable devices are expensive and inconvenient to use; the other is based on vision systems. This kind of method collects image information through sensors, and then performs image processing and recognition process, which brings good human-computer interaction to users. How to improve the recognition accuracy and reduce the recognition time is the difficulty of this kind of method all the time.

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
  • Chinese gesture language recognition method based on convolutional neural network
  • Chinese gesture language recognition method based on convolutional neural network
  • Chinese gesture language recognition method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The network structure of convolutional neural network is mainly composed of convolutional layer, pooling layer and fully connected layer. The convolutional layer is also a feature extraction layer. It extracts different features of the image by using different convolution kernels to perform convolution operations on the input image. The convolution operation makes the parameters of the convolution kernels shared in different positions of the image, which can greatly reduce the model The parameters of , reducing the training time, and the extracted features have nothing to do with the spatial position, the expression is as follows:

[0014]

[0015] in, It is the jth neuron of the L layer; f( ) represents the nonlinear activation function function, which has many common functions, such as Sigmoid function, hyperbolic tangent function (tanh), linear correction unit (ReLU), etc.; W Is the convolution kernel; * represents the convolution operation; b is the weight.

...

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 relates to a Chinese gesture language recognition method based on a convolutional neural network. The method comprises the following steps of collecting various gesture pictures of Chinese gesture language, and obtaining multiple gesture samples through gesture segmentation and preprocessing; dividing an obtained gesture sample dataset into a training set, a verifying set and a testing set according to the proportion of 5:1:1; building seven layers of convolutional neural network CNN models, wherein the convolutional neural network CNN models include three convolutional layers, two pooling layers and one fully-connecting layer; using the gesture features of the CNN model training set to set the image quantity of batchsize after batching every time, and selecting the featuresafter each convulsion through maximal pooling; after the last convolution of layers, classifying feature vectors through a Softmax function, classifying the result, comparing labels, and updating theweight of the model; comparing the accuracy of the verification set after each iteration, and comparing the result with the last verification result; if the accuracy is lowered, continuing the iteration, and if the accuracy is not lowered, stopping the iteration.

Description

technical field [0001] The invention belongs to the field of gesture recognition. Background technique [0002] At present, gesture recognition methods are mainly divided into two categories. One is the method based on wearable devices. Although the real-time performance is better, wearable devices are expensive and inconvenient to use; the other is based on vision systems. This kind of method collects image information through sensors, and then performs image processing and recognition process, which brings good human-computer interaction to users. How to improve the recognition accuracy and reduce the recognition time has always been the difficulty of this kind of method. [0003] In recent years, with the significant improvement of computer graphics processing capabilities, deep learning has made major breakthroughs in speech recognition, image classification and other fields. Deep learning uses a multi-layer nonlinear deep neural network to classify and process input im...

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): G06K9/00G06N3/04
CPCG06V40/28G06N3/045
Inventor 吕辰刚鲍志强
Owner TIANJIN UNIV
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
Eureka Blog
Learn More
PatSnap group products