Abstract | ||
---|---|---|
Recently, convolutional neural networks have demonstrated excellent prediction performance in hyperspectral image (HSI) classification. However, in traditional methods, the specific design of classification networks requires extensive professional knowledge, and the fixed network architecture lacks adaptability to different datasets. In this paper, a spectral feature perception evolving network (SFPEN), which is a dataset-oriented network method, is proposed. First, to overcome the drawbacks of traditional methods and improve the classification accuracy, an SFPEN driven by an evolutionary algorithm is proposed. The SFPEN automatically designs the network architecture based on a given HSI. Second, spectral feature perception modules are designed to extract the spectral features of HSIs and eliminate redundant information in the HSI narrow bands. Finally, a two-stage network fitness evaluation strategy is designed to reduce the number of training epochs of numerous networks and improve the efficiency of the network evaluation. The experimental results for the available datasets indicate that the proposed method achieves high classification accuracy and demonstrates great adaptability to different datasets. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.knosys.2022.109845 | Knowledge-Based Systems |
Keywords | DocType | Volume |
Hyperspectral images,Evolving self-adaptive network,Spectral feature perception | Journal | 256 |
ISSN | Citations | PageRank |
0950-7051 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiao Shi | 1 | 0 | 0.68 |
Hao Wang | 2 | 440 | 127.79 |
Chunhui Tan | 3 | 0 | 0.34 |
Yu Lei | 4 | 7 | 5.92 |
Gwanggil Jeon | 5 | 596 | 117.99 |