Bio-Inspired Structure Representation Based Cross-View Discriminative Subspace Learning via Simultaneous Local and Global Alignment

Table 1

Classification results (%) of all methods on original CMU-PIE dataset.

Methods	C1	C2	C3	C4	C5	C6
LDA	62.96 ± 0.66	66.76 ± 0.58	62.16 ± 1.20	61.50 ± 1.14	56.54 ± 0.55	61.83 ± 0.88
PCA	48.28 ± 0.59	50.50 ± 0.72	49.07 ± 0.95	48.43 ± 1.11	45.51 ± 0.84	49.68 ± 0.43
LatLRR	65.10 ± 0.97	66.61 ± 1.57	62.47 ± 1.34	63.09 ± 2.08	61.04 ± 1.87	60.42 ± 0.73
LPP	62.40 ± 0.80	60.17 ± 0.27	61.97 ± 0.33	62.13 ± 0.45	58.34 ± 0.10	60.72 ± 0.28
SRRS	95.35 ± 1.05	91.66 ± 1.84	95.82 ± 1.35	90.22 ± 0.26	96.04 ± 1.07	87.16 ± 0.55
RCVL	97.14 ± 0.09	93.70 ± 0.59	97.26 ± 0.04	92.99 ± 0.12	97.55 ± 0.06	88.60 ± 0.03
Ours	98.27 ± 0.11	93.47 ± 0.06	98.15 ± 0.08	91.69 ± 0.08	98.53 ± 0.02	90.27 ± 0.14