Experimental Analysis of Skin Color Detection and Automated Recognition for Finger Spelling

DOI IR Web Site

Bibliographic Information

Other Title
  • 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
  • アルファベット ユビ モジ ノ ハダイロ チュウシュツ ト ニンシキ ニ カンスル キソテキ ケンキュウ

Search this article

Abstract

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.

Journal

Keywords

Details 詳細情報について

Report a problem

Back to top