Kernel principal component analysis network for image classification
This work addresses image classification challenges, particularly in handling nonlinear features, but is incremental as it builds upon existing PCANet methods.
The authors tackled the problem of classifying nonlinear features with linear classifiers by proposing a kernel principal component analysis network (KPCANet), which maps data into a higher space for linear separability and uses a two-layer network to extract principal components; experimental results show it outperforms PCANet in tasks like face and object recognition.
In order to classify the nonlinear feature with linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network (KPCANet) is proposed. First, mapping the data into higher space with kernel principal component analysis to make the data linearly separable. Then building a two-layer KPCANet to obtain the principal components of image. Finally, classifying the principal components with linearly classifier. Experimental results show that the proposed KPCANet is effective in face recognition, object recognition and hand-writing digits recognition, it also outperforms principal component analysis network (PCANet) generally as well. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.