Classification of hyperspectral images based on two-channel convolutional neural network combined with support vector machine algorithm

Abstract. Our study uses artificial intelligence and machine learning methods for dimensionality reduction, feature extraction, and classification of hyperspectral remote sensing images to detect subtle differences between different spectra. Our study also used hyperspectral remote sensing image data gathered by airborne visible infrared imaging spectrometer over the Indian Pines and Salinas test sites. Based on experimental analysis and comparison of mainstream classifiers and advanced algorithms, we propose a new classification mode for the hyperspectral image based on a two-channel fusion of convolutional neural network-support vector machine (CNN-SVM). This model gives full play to the advantages of CNN in feature extraction and the advantages of SVM in the classification. It also maximizes the generalization and accuracy of classification. The CNN is based on two-channel feature extraction, including spatial features and spectral features, which utilizes the characteristics of hyperspectral remote sensing images for classification. Experimental results show that the research is both theoretically and practically significant for improving the quality and accuracy of identification and classification.

[1]  V. V. Kozoderov,et al.  A system for processing hyperspectral imagery: application to detecting forest species , 2014 .

[2]  HosseinifardBehshad,et al.  Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal , 2013 .

[3]  Qi Wang,et al.  Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[4]  Hongyi Zhang,et al.  mixup: Beyond Empirical Risk Minimization , 2017, ICLR.

[5]  Yingcai Xiao,et al.  Research and application of combined kernel SVM in dynamic voiceprint password authentication system , 2017, 2017 IEEE 9th International Conference on Communication Software and Networks (ICCSN).

[6]  Yihong Gong,et al.  Advances in Multimedia Information Processing - PCM 2016 , 2016, Lecture Notes in Computer Science.

[7]  Junjun Jiang,et al.  Spectral-Spatial Feature Extraction of Hyperspectral Images Based on Propagation Filter , 2018, Sensors.

[8]  Huaping Luo,et al.  Based on multi-scale hyperspectral near ground remote to sensing the quality of Southern Xinjiang jujube , 2019, Symposium on Novel Photoelectronic Detection Technology and Application.

[9]  Yu He,et al.  Prediction of coal and gas outburst grade based on factor analysis and SVM model , 2019, RICAI 2019.

[10]  Yukinobu Hoshino,et al.  Evaluation of Optimization Methods for Neural Network , 2016, 2016 Joint 8th International Conference on Soft Computing and Intelligent Systems (SCIS) and 17th International Symposium on Advanced Intelligent Systems (ISIS).

[11]  Jianbin Qiu,et al.  A novel approach to hyperspectral band selection based on spectral shape similarity analysis and fast branch and bound search , 2014, Eng. Appl. Artif. Intell..

[12]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[13]  Helwig Hauser,et al.  Designing Progressive and Interactive Analytics Processes for High-Dimensional Data Analysis , 2017, IEEE Transactions on Visualization and Computer Graphics.

[14]  Jie Feng,et al.  Joint Multilayer Spatial-Spectral Classification of Hyperspectral Images Based on CNN and Convlstm , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[15]  Nema Salem,et al.  Data dimensional reduction and principal components analysis , 2019, Procedia Computer Science.

[16]  Balázs Deák,et al.  Classification of Herbaceous Vegetation Using Airborne Hyperspectral Imagery , 2015, Remote. Sens..

[17]  Raúl Siche,et al.  Determination of starch content in adulterated fresh cheese using hyperspectral imaging , 2018 .

[18]  Richard Gloaguen,et al.  The Need for Accurate Geometric and Radiometric Corrections of Drone-Borne Hyperspectral Data for Mineral Exploration: MEPHySTo - A Toolbox for Pre-Processing Drone-Borne Hyperspectral Data , 2017, Remote. Sens..

[19]  Yuan Ma,et al.  Voxel-Based Morphometry: Improving the Diagnosis of Alzheimer’s Disease Based on an Extreme Learning Machine Method from the ADNI cohort , 2019, Neuroscience.

[20]  Lênio Soares Galvão,et al.  Hyperspectral Remote Sensing for Detecting Soil Salinization Using ProSpecTIR-VS Aerial Imagery and Sensor Simulation , 2017, Remote. Sens..

[21]  Charles K. Toth,et al.  Remote sensing platforms and sensors: A survey , 2016 .

[22]  Hairong Wang,et al.  Sparse representation based lossy hyperspectral data compression , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[23]  Monji Kherallah,et al.  Hybrid TDNN-SVM Algorithm for Online Arabic Handwriting Recognition , 2016, HIS.

[24]  M. Scully,et al.  Single-shot chemical detection and identification with compressed hyperspectral Raman imaging. , 2017, Optics letters.

[25]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[27]  C. Devi Arockia Vanitha,et al.  Gene Expression Data Classification Using Support Vector Machine and Mutual Information-based Gene Selection☆ , 2015 .

[28]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[29]  Jon Atli Benediktsson,et al.  Scalable semi-supervised classification of hyperspectral remote sensing data with spectral and spatial information , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[30]  Xiaogang Wang,et al.  Spindle Net: Person Re-identification with Human Body Region Guided Feature Decomposition and Fusion , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Rashedur M. Rahman,et al.  Classification Based on Spectral Characterization and Analysis of Land Cover Change in Dhaka , 2018, 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS).

[32]  Shanjun Mao,et al.  Spectral–spatial classification of hyperspectral images using deep convolutional neural networks , 2015 .

[33]  Qi Kunlun,et al.  Sparse coding-based correlaton model for land-use scene classification in high-resolution remote-sensing images , 2016 .

[34]  Bin Chen,et al.  Forest Types Classification Based on Multi-Source Data Fusion , 2017, Remote. Sens..

[35]  Zhongming Zhao,et al.  Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[36]  Li Zhuo,et al.  Hyperspectral remote sensing image retrieval system using spectral and texture features. , 2017, Applied optics.

[37]  Le Wu,et al.  Predicting Aesthetic Radar Map Using a Hierarchical Multi-task Network , 2018, PRCV.

[38]  Liangpei Zhang,et al.  Spectral–Spatial Sparse Subspace Clustering for Hyperspectral Remote Sensing Images , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Jing Qian,et al.  Spectral Similarity Assessment Based on a Spectrum Reflectance-Absorption Index and Simplified Curve Patterns for Hyperspectral Remote Sensing , 2016, Sensors.

[40]  Jon Atli Benediktsson,et al.  Support Tensor Machines for Classification of Hyperspectral Remote Sensing Imagery , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[41]  Mark S. Nixon,et al.  Feature extraction & image processing for computer vision , 2012 .

[42]  Uwe Soergel,et al.  Nonlinear Feature Normalization for Hyperspectral Domain Adaptation and Mitigation of Nonlinear Effects , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[43]  J. Shutler,et al.  Spatial assessment of intertidal seagrass meadows using optical imaging systems and a lightweight drone , 2018 .

[44]  Jonathan Cheung-Wai Chan,et al.  Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[45]  Guo Cao,et al.  Cascaded Random Forest for Hyperspectral Image Classification , 2018, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[46]  Baijian Yang,et al.  Big Data Dimension Reduction Using PCA , 2016, 2016 IEEE International Conference on Smart Cloud (SmartCloud).

[47]  S. Nedevschi,et al.  PCA type algorithm applied in face recognition , 2012, 2012 IEEE 8th International Conference on Intelligent Computer Communication and Processing.