A method of AR system gesture recognition method

Abstract

An AR system gesture recognition method based on convolutional neural network combined with user habitual behavior analysis, including the following steps: Step 1: User habitual gesture image acquisition: a group of gestures is randomly provided by the user, and this group of gestures is used as a standard gesture, Collect this group of gesture images and mark it as the standard group; construct its corresponding actual label category according to the gesture model diagram of the standard group; set different label categories to trigger the corresponding AR system specified functions; Step 2: Gesture area image detection: separately for the standard group , the gesture images of the training sample group and the test sample group are used for gesture area image detection to realize the segmentation of skin color and non-skin color areas in the image; step 3: convolutional neural network to realize gesture feature recognition: design a preliminary structural model of convolutional neural network, Train and test tune the convolutional neural network model with sample data, and feed the binarized image directly into the convolutional neural network. The gesture recognition accuracy rate of the present invention is higher, and the cost of additional equipment is lower.

Description

technical field [0001] The invention relates to a gesture recognition method for an augmented reality (AR) system, in particular to a gesture recognition method based on a convolutional neural network combined with user habitual behavior analysis. Background technique [0002] In recent years, as artificial intelligence continues to enter people's field of vision, augmented reality technology (AR technology) has gradually become a hot topic. Augmented reality technology applies virtual information to the real world through computer technology, and the real environment and virtual objects are superimposed on the same screen or exist simultaneously in the same space in real time. Among them, human-computer interaction technology is particularly important. As a way of expression, gesture is usually regarded as one of the important means of human-computer interaction, and gesture recognition has also attracted many scholars' research. [0003] Chen Zhihua and others proposed a...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing AR system, such as low gesture recognition accuracy and high cost of additional equipment, the present invention proposes a convolutional neural network combined with user habitual behavior analysis with high gesture recognition accuracy and low additional equipment cost. AR system gesture recognition method

Images