Meta-learning for Image Processing Based on Case-Based Reasoning - Computational Intelligence in Healthcare: Advanced Methodologies - page 233

Fig. 17. Clustering of Test Images into Groups based on the Segmentation Parameters

Table 4. Parameters for the image class neurone Fig. 18a) to Fig. 18d)

ImageName a b T

neu1r.bmp 2 1 1

neu2r.bmp 0,25 1 1

neu3r.bmp 2 1 1

neu4r.bmp 0,75 2 1

(a) neu1 (b) neu2 (c) neu3 (d) neu4

(2, 1, 1) BS=107 (0.25, 1, 1) BS=104 (2, 1, 1) BS=98 (0.75, 2, 1) BS=95

(e) Labelled image
neu1

(f) Labelled image
neu3

(g) Labelled image
neu3

(h) Labelled image
neu4

Fig. 18 a-h. The different neuron images with their best segmentation, the parameters (a,b,T),
and the number of basins BS