next up previous contents
Next: Experiments on the Fault Up: Gray Scale Picture Recognition Previous: Manually Distorted Pictures

Noisy Pictures

Another comparison was made on the ability to recognize noisy inputs. The noise on the pictures was generated randomly. The noise-level is the probability for each pixel to be altered to a random value in the interval [0,1] (an uniform distribution was used). In Figure 7.8 pictures with different noise-levels are shown.

 figure1129
Figure 7.8:  Examples of Noisy Test Pictures.

The modular network could recognize pictures with a significant higher noise-level than the single MLP; the results are shown in Figure 7.9.

 figure1135
Figure 7.9:  The Performance on Noisy Inputs.

From the above experiments it can be seen that the modular network has superior generalization abilities on this type of high dimensional input vectors.


next up previous contents
Next: Experiments on the Fault Up: Gray Scale Picture Recognition Previous: Manually Distorted Pictures

Albrecht Schmidt
Mit Okt 4 16:45:34 CEST 2000