Artificial language contains a number of technologies and algorithms that meet the needs of human interaction, especially deep learning algorithms that help in distinguishing and detecting the movement of a moving hand. Where possible, by tracking and detecting the movement of the hands, sign language is distinguished, and this technology plays an important role in breaking the communication barrier between the deaf community and the world. The research presented is a method to distinguish the movement of the hands to detect Arabic sign language, by extracting features from still and moving images using the linear discriminant analysis algorithm, and using these features in a one-dimensional convolutional neural network, and also applying the vgg-16 network and comparing the results, where high performance was obtained. Up to 99.98%.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Dynamic Hand Gesture Recognition Using a One-Dimensional Convolutional Neural Network and VGG-16

  • Maha Sabri Altememe,
  • Wael Mahdi Brich

摘要

Artificial language contains a number of technologies and algorithms that meet the needs of human interaction, especially deep learning algorithms that help in distinguishing and detecting the movement of a moving hand. Where possible, by tracking and detecting the movement of the hands, sign language is distinguished, and this technology plays an important role in breaking the communication barrier between the deaf community and the world. The research presented is a method to distinguish the movement of the hands to detect Arabic sign language, by extracting features from still and moving images using the linear discriminant analysis algorithm, and using these features in a one-dimensional convolutional neural network, and also applying the vgg-16 network and comparing the results, where high performance was obtained. Up to 99.98%.