2026-03-15T09:05:57Z https://jin-ai.repo.nii.ac.jp/oai

oai:jin-ai.repo.nii.ac.jp:00001062 2023-06-20T16:11:40Z 14:74

アルファベット指文字の肌色抽出と認識に関する基礎的研究 Experimental Analysis of Skin Color Detection and Automated Recognition for Finger Spelling 島田, 貢明 シマダ, ミツアキ Shimada, Mitsuaki 指文字 手話 肌色抽出 画像処理 画像認識 ニューラルネットワーク finger spelling sign language skin color detection image processing image recognition neural network This research is concerned with automated recognition of sign language. In this paper, new algorithm using Neural Network which recognizes finger spelled word of American Sign Language (ASL) is proposed.Experiment is also conducted using actual video of finger spelled words. This is a challenging task since the ASL alphabets are expressed by the various figure of one hand. The captured input image in RGB is converted to HSV color space, because it is more related to human color perception. Automated recognition experiment using proposed algorithm is done to 26 characters of ASL finger spelling. According to the result of experimental analysis, it is proved that the algorithm proposed in this paper is effective in finger spelling recognition. 仁愛女子短期大学 2011-03-31 jpn departmental bulletin paper VoR https://doi.org/10.57426/00001056 https://jin-ai.repo.nii.ac.jp/records/1062 10.57426/00001056 09138587 仁愛女子短期大学研究紀要 43 1 6 https://jin-ai.repo.nii.ac.jp/record/1062/files/vol.43_p1-6.pdf application/pdf 1.7 MB 2022-10-27