Meta-learning for Image Processing Based on Case-Based Reasoning - Computational Intelligence in Healthcare: Advanced Methodologies - page 247

(a) Image neu1 (b) Gradient image of Fig. 36a (c) Image local minima of Fig.

36b

(d) Image neu3 (e) Gradient image of Fig. 36e (f) Image local minima of Fig.

36

Fig. 36. Orginal image and the local minimas from the gradient image

Fig. 37. Dendrogram from similarity measure from [18]

More promising are probably the determination of the distances from one regional
minima to all the surrounding minima up to a predefined area and the calculation of
the statistical distribution. Then the problem would be to compare the distribution of
two images. We will further evaluate this idea in another study.