Skip to main content
. Author manuscript; available in PMC: 2013 May 18.
Published in final edited form as: IEEE Trans Pattern Anal Mach Intell. 2010 Nov;32(11):10.1109/TPAMI.2010.28. doi: 10.1109/TPAMI.2010.28

Fig. 17.

Fig. 17

Comparative results of the proposed algorithm implemented with SDA, SubAdaBoost (denoted SAB in the figure), LDA, AdaBoost (denoted AB) and PCA. The left plot summarizes the percentage of error, EA. The right plot summarizes the detection rate of each of the algorithms. These results are the average over all the images in the AR, XM2VT and ASL databases.