A Novel Semi-Supervised Learning Method Based on Fast Search and Density Peaks

Figure 15

In EOC_1 experiment, the visualization results of the first two steps of the S²DP and WKFDA+DP+S³VM algorithms when the number of the samples is 21. (a) WKFDA features: represents the learning set and represents the initial labeled samples; (b) actual classification map of WKFDA features after DP clustering has been carried: represents the clustering core and represents the clustering halo; (c) true classification map of (b): represents the clustering core, represents the clustering error sample, and represents the sample of the next step of the algorithm to be identified.

(a)

(b)

(c)