A gesture recognition method based on a convolutional neural network and an anti-convolutional neural network

Abstract

The invention discloses a gesture recognition method based on a convolutional neural network and an anti-convolution neural network. For certain specific types of gestures, a training sample is generated by using the anti-convolution neural network, so that an over-fitting problem when a model is trained can be solved. In addition, the convolutional neural network is used for gesture recognition,so that the recognition accuracy and the efficiency can be effectively improved, and the real-time gesture recognition can be achieved. According to the gesture recognition method, the convolutional neural network and the anti-convolutional neural network are combined and applied to gesture recognition, compared with a traditional recognition method, the neural network has the advantages that convolution can be directly carried out on the neural network and image pixels, image features are extracted from the image pixels, and the processing mode is closer to the processing mode of a human brain vision system.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a gesture recognition method based on a convolutional neural network and an anti-convolutional neural network. Background technique [0002] In recent years, with the rapid development of science and technology, the way of human-computer interaction has also been greatly changed. Various new types of human-computer interaction have also appeared in the public's field of vision. The interaction mode of mouse and keyboard has changed to touch screen and voice. The form of interaction becomes diversified and humanized. However, a more efficient form of interaction is to allow machines to understand human body language. Gestures are the most common of all types of body language. Therefore, it can be used as a simple and free means of human-computer interaction, and has a very broad application prospect. [0003] When performing gesture-based human-computer interaction, a very import...

AI Technical Summary

Problems solved by technology

[0007] Now is the era of information technology and the era of big data. It is difficult for traditional gesture recognition algorithms to solve such a large amount of data. Using these algorithms may waste a lot of time

And when there are many types of gestures, according to the traditional gesture recognition method to identify different types of gestures, it can only achieve better recognition results on a small number of gestures, and most of the gestures cannot achieve satisfactory results, that is, traditional methods. The pertinence is relatively strong, and it may have a good segmentation effect on certain types of gestures, but it cannot be applied to other types of gestures, that is, it does not have wide applicability.

When convolutional neural networks are used for gesture recognition, overfitting in training is a very common phenomenon, and this is indeed a problem that cannot be ignored. At the same time, a large number of experiments have also proved this problem, which seriously affects the final recognition of the model. Effect

Images