Color Image Classification via Quaternion Principal Component Analysis Network
This work addresses improved color image classification for computer vision applications, but it is incremental as it extends an existing method.
The paper tackled the problem of degraded performance of PCANet on color images by proposing QPCANet, an extension that incorporates spatial distribution information and intra-class invariance, resulting in higher classification accuracy on datasets like Caltech-101 and UC Merced Land Use.
The Principal Component Analysis Network (PCANet), which is one of the recently proposed deep learning architectures, achieves the state-of-the-art classification accuracy in various databases. However, the performance of PCANet may be degraded when dealing with color images. In this paper, a Quaternion Principal Component Analysis Network (QPCANet), which is an extension of PCANet, is proposed for color images classification. Compared to PCANet, the proposed QPCANet takes into account the spatial distribution information of color images and ensures larger amount of intra-class invariance of color images. Experiments conducted on different color image datasets such as Caltech-101, UC Merced Land Use, Georgia Tech face and CURet have revealed that the proposed QPCANet achieves higher classification accuracy than PCANet.