查看文章

Sign language is the language of gestures used for non-verbal communication. This paper deals with alphabets and digit signs recognition from Pakistan Sign Language (PSL). The deep pixels-based analysis is pursued for the recognition of fingers (from index to small finger) while thumb position is determined through Template Matching. After fingers identification, the isolated signs are recognized based on finger states of being raised or lowered besides thumb’s position in 2D. For a quick recognition, signs are categorized into seven groups. The algorithm identifies these groups following a model of seven phases. The system’s accuracy achieved a satisfactory level of 84.2% when evaluated with signs comprising 180 digits and 240 alphabets.