Real-time recognition method for static sign language based on improved single-time multi-objective detector

Abstract

The invention relates to a real-time recognition method for a static sign language based on an improved single-time multi-objective detector, which comprises the steps of performing preprocessing on astatic sign language sample image; building a reinforced static sign language image data set; building a deep learning network based on the improved single-time multi-objective detector, wherein thedeep learning network is divided into a basic network layer and an additional convolution feature layer, the basic network layer is used for feature extraction and converting an input image into multi-dimensional feature representation, and the additional convolution layer is a feature selection strategy, the category score and the position offset of a fixed group of default bounding boxes on a feature map are predicted by using a small convolution filter, and different scales of predictions are generated from different scales of feature maps; and training the network by using the static signlanguage data set, and inputting sign language video acquired by a camera in real time into the well trained network so as to realize real-time recognition for the static sign language. The real-timerecognition method greatly improves the recognition speed while ensuring the recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of sign language recognition, in particular to a static sign language real-time recognition method based on an improved single-shot multi-target detector. Background technique [0002] Sign language is an effective way for deaf people to communicate with gestures instead of normal speech. Research on sign language recognition can help deaf-mute people, especially some deaf-mute people who have not received a good education, and can also help communication between deaf-mute people and normal people; sign language recognition is also a convenience for human-computer interaction Research on sign language recognition can promote the development of other fields such as machine intelligence operation, operation of mobile device terminals, access control systems, remote control, etc. Further, research on sign language recognition can assist computers in understanding human language. [0003] Sign language recognit...

AI Technical Summary

Problems solved by technology

[0007] The above methods have become milestones in the field of detection and recognition. Although the accuracy is relatively good, these methods are too computationally intensive for embedded systems. Even for high-end hardware, they are too slow for real-time or near-real-time applications, or sacrifice Detection accuracy in exchange for time

Images