Image Recognition and Extraction on Computerized Vision for Sign Language Decoding

Abstract

The image recognition method is a significant process in addressing contemporary global issues. Numerous image detection, analysis, and classification strategies are readily available, but the distinctions between these approaches remain somewhat obscure. Therefore, it is essential to clarify the differences between these techniques and subject them to rigorous analysis. This study utilizes a dataset comprising standard American Sign Language (ASL) and Indian Sign Language (ISL) hand gestures captured under various environmental conditions. The primary objective is to accurately recognize and classify these hand gestures based on their meanings, aiming for the highest achievable accuracy. A novel method for achieving this goal is proposed and compared with widely recognized models. Various pre-processing techniques are employed, including principal component analysis and histogram of gradients. The principal model incorporates Canny edge detection, Oriented FAST and Rotated BRIEF (ORB), and the bag of words technique. The dataset includes images of the 26 alphabetical signs captured from different angles. The collected data is subjected to classification using Support Vector Machines to yield valid results. The results indicate that the proposed model exhibits significantly higher efficiency than existing models.