SIGN LANGUAGE IMAGE CLASSIFICATION DEVICE AND SIGN LANGUAGE IMAGE CLASSIFICATION PROGRAM

To enable generation of sign language image dataset for machine learning.SOLUTION: A sign language image classification device according to an embodiment of the present invention comprises a key point extraction unit configured to extract key points of hands of a sign language speaker from a sign la...

Full description

Saved in:
Bibliographic Details
Main Author KAJIYAMA TAKESHI
Format Patent
LanguageEnglish
Japanese
Published 10.08.2023
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:To enable generation of sign language image dataset for machine learning.SOLUTION: A sign language image classification device according to an embodiment of the present invention comprises a key point extraction unit configured to extract key points of hands of a sign language speaker from a sign language image, a computation unit configured to compute feature quantities using the key points, and a classification unit configured to classify the sign language image according to the feature quantities by a clustering method.SELECTED DRAWING: Figure 5 【課題】機械学習用の手話画像のデータセットを生成する。【解決手段】本発明の一実施形態に係る手話画像分類装置は、手話画像から手話の話者の手のキーポイントを抽出するキーポイント抽出部と、前記キーポイントを用いて特徴量を算出する算出部と、前記特徴量をもとに、前記手話画像をクラスタリング手法により分類する分類部と、を備える。【選択図】図５
Bibliography:Application Number: JP20220012724