结合改进LBP和SRC的高光谱图像分类研究

doi:10.3778/j.issn.1002-8331.2109-0420

摘要/Abstract

摘要： 针对传统局部二值模型（local binary pattern，LBP）提取高光谱图像纹理特征信息量庞大的难题，提出一种基于对称旋转不变等价局部二值模型（symmetrical rotation invariant uniform LBP，SRIULBP）的高光谱图像特征提取方法，以缩减特征维度；针对稀疏表示分类（sparse representation classification，SRC）模型中稀疏字典冗余的缺陷，采用近邻思想，提出最近邻稀疏表示（nearest neighbor SRC，NNSRC）分类方法，实现高光谱图像的高效、高准确度分类。数据实验结合表明，SRIULBP能快速提取图像特征，提出的分类方法不仅在分类精度上优于其他稀疏表示分类算法，并且具有更强的时效性与泛化能力。

关键词: 高光谱图像分类, 改进局部二值模型, 特征提取, 最近邻稀疏表示

Abstract: Aiming at the problem of the traditional local binary pattern（LBP） extracting the huge amount of hyperspectral image texture feature information, a hyperspectral image feature extraction method based on the symmetrical rotation invariant uniform LBP（SRIULBP） is proposed to reduce the feature dimension;aiming at the defect of sparse dictionary redundancy in the sparse representation classification（SRC） model, the nearest neighbor SRC（NNSRC） method is proposed by adopting the idea of nearest neighbors to achieve efficient and high accuracy classification of hyperspectral images. The combination of data experiments shows that SRIULBP can quickly extract image features. The proposed classification method is not only superior to other sparse representation classification algorithms in classification accuracy, but also has stronger timeliness and generalization capabilities.

Key words: hyperspectral image classification, improved local binary pattern, feature extraction, nearest neighbor sparse representation

龚渝, 赵圣璞, 徐俊洁, 赵慧敏. 结合改进LBP和SRC的高光谱图像分类研究[J]. 计算机工程与应用, 2023, 59(2): 253-260.

GONG Yu, ZHAO Shengpu, XU Junjie, ZHAO Huimin. Research on Hyperspectral Image Classification Combining Improved LBP and SRC[J]. Computer Engineering and Applications, 2023, 59(2): 253-260.

参考文献

[1] 冯天时，庞治国，江威，等.高光谱遥感技术及其水利应用进展[J].地球信息科学学报，2021，23（9）：1646-1661.
FENG T S，PANG Z G，JIANG W，et al.Progress and prospects of hyperspectral remote sensing technology and its application in water conservancy research[J].Journal of Geo-information Science，2021，23（9）：1646-1661.
[2] BROWN A J，VIVIANO C E，GOUDGE T A.Olivine-carbonate mineralogy of the Jezero Crater Region[J].Journal of Geophysical Research：Planets，2020，125（3）：e2019JE006011.
[3] 刘启超，肖亮，刘芳，等.SSCDenseNet：一种空-谱卷积稠密网络的高光谱图像分类算法[J].电子学报，2020，48（4）：751-762.
LIU Q C，XIAO L，LIU F，et al.SSCDenseNet：a spectral-spatial convolutional dense network for hyperspectral image classification[J].Acta Electronica Sinica，2020，48（4）：751-762.
[4] 吕昊远，俞璐，周星宇，等.半监督深度学习图像分类方法研究综述[J].计算机科学与探索，2021，15（6）：1038-1048.
LYU H Y，YU L，ZHOU X Y，et al.Review of semi-supervised deep learning image classification methods[J].Journal of Frontiers of Computer Science and Technology，2021，15（6）：1038-1048.
[5] ZHENG J，FENG Y，BAI C，et al.Hyperspectral image classification using mixed convolutions and covariance pooling[J].IEEE Transactions on Geoscience and Remote Sensing，2020，59（1）：522-534.
[6] JUNG J Y，KIM S W，YOO C H，et al.LBP-ferns-based feature extraction for robust facial recognition[J].IEEE Transactions on Consumer Electronics，2017，62（4）：446-453.
[7] MASOOD K，RAJPOOT N.Texture based classification of hyperspectral colon biopsy samples using CLBP[C]//IEEE International Symposium on Biomedical Imaging，2009：1011-1014.
[8] PENG B，LI W，XIE X M，et al.Weighted-fusion-based representation classifiers for hyperspectral imagery[J].Remote Sensing，2015，7（11）：14806-14826.
[9] 职露，余旭初，邹滨，等.多层级二值模式的高光谱影像空谱分类[J].武汉大学学报（信息科学版），2019，44（11）：1659-1666.
ZHI L，YU X C，ZHOU B，et al.Space-spectral classification of hyperspectral images based on multi-layer binary mode[J].Geomatics and Information Science of Wuhan University，2019，44（11）：1659-1666.
[10] 刘渭滨，邹智元，邢薇薇.模式分类中的特征融合方法[J].北京邮电大学学报，2017，40（4）：1-8.
LIU W B，ZHOU Z Y，XING W W.Feature fusion methods in pattern classification[J].Journal of Beijing University of Posts and Telecommunications，2017，40（4）：1-8.
[11] WRIGHT J，YANG A J，GANESH A，et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2009，31（2）：210-227.
[12] RAFIEZADEH S K，GHAMISI P，RASTI B，et al.Data fusion using a multi-sensor sparse-based clustering algorithm[J].Remote Sensing，2020，12（23）：4007.
[13] CHEN Y，NASRABADI N M，TRAN T D.Hyperspectral image classification using dictionary-based sparse representation[J].IEEE Transactions on Geoscience and Remote Sensing，2011，49（10）：3973-3985.
[14] TU B，ZHANG X F，KANG X D，et al.Hyperspectral image classification via fusing correlation coefficient and joint sparse representation[J].IEEE Geoscience & Remote Sensing Letters，2018，15（3）：340-344.
[15] 于亚风.基于局部二值模式的纹理特征研究与应用[D].成都：西南交通大学，2017.
YU Y F.The research and application of texture feature based on LBP[D].Chengdu：Southwest Jiaotong University，2017.
[16] 刘瑞香.基于多尺度局部二值模式的高光谱图像分类算法研究[D].西安：西安石油大学，2016.
LIU R X.Research on hyperspectral image classification algorithm based on multi-scale local binary pattern[D].Xi’an：Xi’an Shiyou University，2016.

[17] WEN J，FANG X，CUI J，et al.Robust sparse linear discriminant analysis[J].IEEE Transactions on Circuits and Systems for Video Technology，2018，29（2）：390-403.

[18] MA L，CRAWFORD M M，TIAN J.Local manifold learningbased-nearest-neighbor for hyperspectral image classification[J].IEEE Transactions on Geoscience & Remote Sensing，2010，48（11）：4099-4109.