Abstract | ||
---|---|---|
The recently proposed principal component analysis network (PCANet) has performed well with respect to the classification of 2-D images. However, feature extraction may perform less well when dealing with multi-dimensional images, since the spatial relationships within the structures of the images are not fully utilized. In this paper, we develop a multilinear principal component analysis network (MPCANet), which is a tensor extension of PCANet, to extract the high-level semantic features from multi-dimensional images. The extracted features largely minimize the intraclass invariance of tensor objects by making efficient use of spatial relationships within multi-dimensional images. The proposed MPCANet outperforms traditional methods on a benchmark composed of three data sets, including the UCF sports action database, the UCF11 database, and a medical image database. It is shown that even a simple one-layer MPCANet may outperform a two-layer PCANet. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ACCESS.2017.2675478 | IEEE ACCESS |
Keywords | Field | DocType |
Deep learning,MPCANet,PCANet,tensor object classification,medical image classification | Data mining,Multilinear principal component analysis,Tensor,Pattern recognition,Computer science,Artificial intelligence,Spatial structure,Multilinear map,Machine learning,Principal component analysis | Journal |
Volume | ISSN | Citations |
5 | 2169-3536 | 4 |
PageRank | References | Authors |
0.40 | 24 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiasong Wu | 1 | 60 | 13.26 |
Shijie Qiu | 2 | 6 | 1.44 |
rui zeng | 3 | 21 | 4.18 |
Youyong Kong | 4 | 96 | 15.23 |
Lotfi Senhadji | 5 | 242 | 31.96 |
Huazhong Shu | 6 | 940 | 90.05 |