Analysis of pixel level features in recognition of real life dual-handed sign language data set

This paper demonstrates the evaluation of various pixel level features for the dual handed sign language data set. Data sets are collected from the real life scenario. We compare the feature extraction methods like Histogram of Orientation Gradient (HOG), Histogram of Boundary Description (HBD) and the Histogram of Edge Frequency (HOEF). The accuracy of HOG and HBD found up to 71.4% and 77.3% whereas the accuracy of HOEF in real life data set is 97.3% and in ideal condition 98.1%.