Using Convolutional Neural Network with Taguchi Parametric Optimization for Knee Segmentation from X-Ray Images

Table 1

Parameters for experiments.

Parameters	Levels
	1	2	3
(a) Architecture	U-Net	Dilated-Resnet	Dense U-Net
(b) Optimizer	Adam	Adadelta	Momentum
(c) Learning rate	0.01	0.001	0.0001