Improved gesture image feature extraction method based on DenseNet network

Abstract

The invention discloses an improved gesture image feature extraction method based on a DenseNet network. Acquiring a gesture to obtain an original gesture image; performing convolution downsampling through a convolution downsampling network structure, selecting feature tensors of a shallow layer and a deep layer, and inputting the feature tensors into a DenseNet-B module of a fused Drop-Path module to obtain two feature tensors; after fusion, obtaining a feature tensor of multi-scale feature fusion, compressing the feature tensor through a transition layer, and inputting the compressed feature tensor into a DenseNet-B module of the fusion Drop-Path module to obtain a feature tensor containing multiple scales and high dimensions; and obtaining a classification result through a global average pooling layer, a full connection layer and a softmax classifier. According to the method, feature tensors of different depths in a down-sampling network structure are included, large target objects and small target objects can be accurately recognized, meanwhile, a Drop-Path module is fused in the DenseNet network, the parameter quantity is effectively reduced while the precision is not reduced, the model training speed is increased, overfitting is prevented, and the gesture recognition accuracy is improved.

Description

technical field [0001] The invention relates to a gesture image extraction method, in particular to an improved gesture image feature extraction method based on a DenseNet network. Background technique [0002] Gesture recognition is a hot human-computer interaction method in recent years, and it is widely used in various fields such as sign language recognition, intelligent monitoring and virtual reality. The initial gesture recognition mainly uses wearable devices to directly detect the angle and spatial position of each joint of the hand and arm. Although these devices can provide good detection results, they are expensive to apply in common fields. In recent years, gesture recognition technology has shifted from wearable devices to machine vision gesture recognition methods and deep learning-based gesture recognition methods. Although gesture recognition technology has made great progress, there are still many challenges in the real environment, such as lighting, target...

AI Technical Summary

Problems solved by technology

[0003] In view of the problem that the features obtained by traditional gesture image feature fusion and recognition methods are difficult to accurately identify images with different proportions of gesture targets in complex backgrounds and the problem of information redundancy that may be caused by dense connections in the DenseNet network, the purpose of the present invention is to propose an adaptive The effective feature extraction and fusion method of images with different proportions of gesture targets can meet the needs of high-precision recognition for gesture targets with different proportions in complex backgrounds

Images