Abstract
In recent years, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, the existing network models have higher model complexity and require more time consumption. Traditional hyperspectral image classification methods tend to ignore the correlation between local spatial features. In this paper, a new hyperspectral image classification method is proposed, which combines two-dimensional Gabor filter with random patch convolution (GRPC) feature extraction to obtain spatial-spectral feature information. The method firstly performs dimensionality reduction through principal component analysis and linear discriminant analysis and extracts the edge texture and spatial information of the image using a Gabor filter for the reduced-dimensional image. Next, the extracted information is convolved with random patches to extract spectral features. Finally, the spatial features and multi-level spectral features are fused to classify the images using the Support Vector Machine classifier. In order to verify the performance of this method, experiments were conducted on three widely used datasets of Indian Pines, Pavia University and Kennedy Space Center. The overall classification accuracy reached 98.09%, 99.64% and 96.53%, which are all higher than other comparison methods. The experimental results reveal the superiority of the proposed method in classification accuracy.
Highlights
In recent years, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results
Methods based on deep learning include Stacked Auto-Encoders (SAE)[6] and Deep Belief Networks (DBN)[7,8], Convolutional Neural Networks (CNN)[9] and Random Patches Networks (RPNet)[10] and so on
This paper proposes a new method based on a two-dimensional Gabor filter and random patches convolution (GRPC), which combines spectral-spatial features for hyperspectral images (HSIs) image classification
Summary
More and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. A new hyperspectral image classification method is proposed, which combines two-dimensional Gabor filter with random patch convolution (GRPC) feature extraction to obtain spatial-spectral feature information. Methods based on deep learning include Stacked Auto-Encoders (SAE)[6] and Deep Belief Networks (DBN)[7,8], Convolutional Neural Networks (CNN)[9] and Random Patches Networks (RPNet)[10] and so on This method learns multi-level nonlinear discriminant features unsupervised from HSI data, has better robustness and discriminant, and can improve the classification accuracy of the model. This paper proposes a new method based on a two-dimensional Gabor filter and random patches convolution (GRPC), which combines spectral-spatial features for HSI image classification. GRPC uses the feature extraction capability of random patches convolution and the advantages of Gabor filters, and realizes the stacking of spectral and spatial features, revealing the importance of spatial structure features that are usually ignored in HSI classification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
