Face recognition using training data with artificial occlusions
Hao Liu, Huiping Duan, Hongyu Cui, Yin Yunjie · 2016
In face recognition for criminal identification, the training data are always clean while the probe data are occluded by sunglasses, scarf or other facial accessories. Occlusions in the probe data severely degrade the recognition performance. We find that introducing artificial occlusions into the training data is helpful in this situation. The incremental training data is decomposed into a class-specific dictionary, a non-class-specific dictionary and a sparse noise or corruption by the sparse and dense hybrid representation framework (SDR). The artificially introduced occlusions play an important role in building the discriminative faces for classification during SDR. Experimental results demonstrate that the proposed method can provide higher recognition accuracy under benchmark face database.