“…In Table 3, we show the F-Score of classification for each frame size (w=5, 6,7,8,9,10,15,20,25,35,45, 55 and 64) and with different alphabet size (a=5, 6, 7, 8, 64, 128). We classified the poses using K-means algorithm into three main classes: class of frontal pose, class of the left view, and class of the right view that group poses in quarter profile (left or right) at full profile.…”