Feature Selection-Based Hierarchical Deep Network for Image Classification

• Published in: IEEE access Vol. 8; pp. 15436 - 15447
• Main Authors: He, Guiqing, Ji, Jiaqi, Zhang, Haixi, Xu, Yuelei, Fan, Jianping
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Classification; Classifiers; Deep learning; Feature extraction; Feature selection; Image classification; Image recognition; multi-level tree classifiers; Ontologies; selective orthogonal; Semantics; Task analysis
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2966651

In this paper, a novel hierarchical deep network is proposed to combine the deep convolutional neural network and the feature selection-based tree classifier efficiently for image classification. First, the concept ontology is built for organizing large-scale image classes hierarchically in a coarse-to-fine fashion. Second, a novel selective orthogonal algorithm is proposed to make sure deep features extracted for each level classifiers more in line with the requirements of different classification tasks. Also, the role of useful feature components in multi-level deep features are improved. The experimental results on three datasets show that adding a feature selection module in a hierarchical deep network can perform better performance in large-scale image classification.