A Sign Language Recognition Method Based on Median Filter and Hu Moment Vector

Abstract

The invention discloses a sign language recognition method based on a median filter and a Hu moment vector, comprising the following steps: Step 1: Acquire a color image of the sign language to be recognized; Step 2: Perform normalization processing on the acquired color image; Step 3 : Perform grayscale transformation processing on the color image; Step 4: Perform median filter processing on the grayscale image; Step 5: Extract the moment invariant of the processed sign language image to obtain the feature vector of the image to be matched; Step 6: Calculate the image to be matched The Euclidean distance between the image and the feature vector of the sign language standard image; Step 7: Recognize sign language. The invention reduces the sensitivity of the image to be recognized to light and noise through image preprocessing such as median filtering and grayscale processing. The Hu feature vector of the image describes the sign language information as a whole, and overcomes the lack of edge information caused by image segmentation. The combination of filtering and Hu moment vector to recognize sign language can effectively improve the effect of sign language recognition and increase the accuracy of sign language recognition.

Description

technical field [0001] The invention relates to the field of simplified processing of digital geometric images, in particular to a sign language recognition method based on median filter and Hu moment vector. Background technique [0002] Along with the research on speech recognition and image processing, more and more researchers are working on helping deaf-mute and normal people communicate normally. At the same time, gesture recognition has received more and more attention in recent years, and has become an equally important recognition method as fingerprints and faces. Sign language is a language that expresses information through actions. "The shape of the hand is its material carrier, and information is transmitted through the shape, position, and movement of the hand." In order to enable deaf-mute or hearing-impaired people to better realize long-distance communication, sign language recognition has become one of the issues that researchers focus on at present. [0...

AI Technical Summary

Problems solved by technology

However, the above scheme has the following disadvantages: (1) The method of using data gloves as an input device is expensive and inconvenient to carry, and it brings a lot of inconvenience to users (such as sweating), so it is difficult to obtain large-scale

Images