Classification of Occluded Images for Large-Scale Datasets With Numerous Occlusion Patterns

Classification of Occluded Images for Large-Scale Datasets With Numerous Occlusion Patterns

Large-scale image datasets with numerous occlusion patterns prevail in real applications. The classification scheme based on subspace decomposition-based estimation with squared l<sub>2</sub> -norm regularization (SDBE_L2) has shown promising performance for the classification of partial...

Full description

Bibliographic Details
Main Authors: Feng Cen, Xiaoyu Zhao, Wuzhuang Li, Fanglai Zhu
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional neural networks
SDBE
occlusion
image classification
principal component analysis
Online Access:https://ieeexplore.ieee.org/document/9199833/

Internet

https://ieeexplore.ieee.org/document/9199833/

Similar Items