Open AccessTGSIFT: Robust SIFT Descriptor Based on Tensor Gradient for Hyperspectral Images
Author(s) -
Li Yanshan,
Fan Leidong,
Xie Weixin
Publication year - 2020
Publication title -
chinese journal of electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.267
H-Index - 25
eISSN - 2075-5597
pISSN - 1022-4653
DOI - 10.1049/cje.2020.08.007
Subject(s) - hyperspectral imaging , scale invariant feature transform , artificial intelligence , computer science , tensor (intrinsic definition) , computer vision , pattern recognition (psychology) , mathematics , image (mathematics) , geometry
This paper proposes a robust sparse descriptor based on tensor theory by using the spatial and spectral information synthetically, namely the Tensor gradient SIFT (TGSIFT), for Hyperspectral image (HSI). TGSIFT integrates both spatial and spectral information and considers the natural vector feature of HSIs. Based on the HSI Gaussian scale space, a new tensor model for HSI is proposed which takes the vectorial nature of HSI into consideration and preserves all the necessary structural information distributed over all the bands. The TGSIFT descriptor is formed based on the model proposed. Experimental results of HSI matching show that the TGSIFT descriptor achieves better matching performance than other SIFT descriptors under different transformations, including illumination change, sensor noise, image rotation, viewpoint change, and scale change.