Optimal Differential Filter on Hexagonal Lattice - Computational Intelligence Paradigms in Advanced Pattern Classification - page 84

(a) Sqr3 × 3 (b) Sqr 5 × 5 (c) Hex 1 (d) Hex 2

(e) Sqr 3 × 3 (f) Sqr 5 × 5 (g) Hex 1 (h) Hex 2

(i) Sqr 3 × 3 (j) Sqr 5 × 5 (k) Hex 1 (l) Hex 2

Fig. 10 Results for f ex 1 . Errors of gradient intensity for four images are mapped to luminance
values in (a), (b), (c) and (d). Errors of orientation detection (arctangent) for four images are
mapped to luminance value as (e), (f), (g) and (h). Errors of orientation detection (Overington)
for four images are mapped to luminance values as (i), (j), (k) and (l).

(a) Sqr 3 3 (b) Sqr 5 5 (c) Hex 1 (d) Hex 2

× ×

(e) Sqr 3 3 (f) Sqr 5 5 (g) Hex 1 (h) Hex 2

× ×

(i) Sqr 3 × 3 (j) Sqr 5 × 5 (k) Hex 1 (l) Hex 2

Fig. 11 Results for f ex 2 . Errors of gradient intensity for four images are mapped to luminance
values in (a), (b), (c) and (d). Errors of orientation detection (arctangent) for four images are
mapped to luminance value as (e), (f), (g) and (h). Errors of orientation detection (Overington)
for four images are mapped to luminance values as (i), (j), (k) and (l).