Research Article

A Modified Active Appearance Model Based on an Adaptive Artificial Bee Colony

Table 13

Proposed and conventional AAM techniques fitting error of (a) CASIA face images dataset, (b) 2.5D face dataset, and (c) UBIRIS dataset.
(a)

Fitting error
ExperimentsConventional AAMAdaptive AAM [41]Proposed AAM

166.824
27.48.576.42
365.625.22
47.25.755.29
5846.40
66.54.874
7463.12
8572.93
97.85.844.33
10765

Average6.496.054.67

(b)

Fitting error
ExperimentsConventional AAMAdaptive AAM [41]Proposed AAM

175.933
26.87.434
386.935
48.84.455.8
5756
65.75.544
7872.58
8653
95.96.924
10763

Average7.026.024.038

(c)

Fitting error
ExperimentsConventional AAMAdaptive AAM [41]Proposed AAM

1652
2563
3671
4834.87
5844
6683
7555
84.4342
96.8762.95
107.8463

Average6.3145.43.082