Low-Resolution Tactile Image Recognition for Automated Robotic Assembly Using Kernel PCA-Based Feature Fusion and Multiple Kernel Learning-Based Support Vector Machine

Table 2

Comparison of recognition accuracies among different methods.

Feature	Classifier	Recognition accuracy; (in %)
FD + GE	𝑘-NN	68.69
FD + GE	SVM	76.17
Kernel PCA-based; feature fusion	SVM	82.13
Kernel PCA-based; feature fusion	MKL-SVM	85.54