HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images
We present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/7/2045 |
| _version_ | 1818036499567869952 |
|---|---|
| author | Haris Ahmad Khan Sofiane Mihoubi Benjamin Mathon Jean-Baptiste Thomas Jon Yngve Hardeberg |
| author_facet | Haris Ahmad Khan Sofiane Mihoubi Benjamin Mathon Jean-Baptiste Thomas Jon Yngve Hardeberg |
| author_sort | Haris Ahmad Khan |
| collection | DOAJ |
| description | We present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study spatial and spectral textures. In this paper we discuss the calibration of the data and the method for addressing the distortions during image acquisition. We provide a spectral analysis based on non-negative matrix factorization to quantify the spectral complexity of the samples and extend local binary pattern operators to the hyperspectral texture analysis. The results demonstrate that although the spectral complexity of each of the textures is generally low, increasing the number of bands permits better texture classification, with the opponent band local binary pattern feature giving the best performance. |
| first_indexed | 2024-12-10T07:11:55Z |
| format | Article |
| id | doaj.art-2dd8074825d24117ad6f50e28b3e35a1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T07:11:55Z |
| publishDate | 2018-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2dd8074825d24117ad6f50e28b3e35a12022-12-22T01:58:01ZengMDPI AGSensors1424-82202018-06-01187204510.3390/s18072045s18072045HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture ImagesHaris Ahmad Khan0Sofiane Mihoubi1Benjamin Mathon2Jean-Baptiste Thomas3Jon Yngve Hardeberg4The Norwegian Colour and Visual Computing Laboratory, NTNU–Norwegian University of Science and Technology, 2815 Gjøvik, NorwayUniv. Lille, CNRS, Centrale Lille, UMR 9189—CRIStAL, Centre de Recherche en Informatique Signal et Automatique de Lille, F-59000 Lille, FranceUniv. Lille, CNRS, Centrale Lille, UMR 9189—CRIStAL, Centre de Recherche en Informatique Signal et Automatique de Lille, F-59000 Lille, FranceThe Norwegian Colour and Visual Computing Laboratory, NTNU–Norwegian University of Science and Technology, 2815 Gjøvik, NorwayThe Norwegian Colour and Visual Computing Laboratory, NTNU–Norwegian University of Science and Technology, 2815 Gjøvik, NorwayWe present a dataset of close range hyperspectral images of materials that span the visible and near infrared spectrums: HyTexiLa (Hyperspectral Texture images acquired in Laboratory). The data is intended to provide high spectral and spatial resolution reflectance images of 112 materials to study spatial and spectral textures. In this paper we discuss the calibration of the data and the method for addressing the distortions during image acquisition. We provide a spectral analysis based on non-negative matrix factorization to quantify the spectral complexity of the samples and extend local binary pattern operators to the hyperspectral texture analysis. The results demonstrate that although the spectral complexity of each of the textures is generally low, increasing the number of bands permits better texture classification, with the opponent band local binary pattern feature giving the best performance.http://www.mdpi.com/1424-8220/18/7/2045hyperspectral imagespectral analysiseffective dimensionspectral LBPtexturedatasetreflectance |
| spellingShingle | Haris Ahmad Khan Sofiane Mihoubi Benjamin Mathon Jean-Baptiste Thomas Jon Yngve Hardeberg HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images Sensors hyperspectral image spectral analysis effective dimension spectral LBP texture dataset reflectance |
| title | HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images |
| title_full | HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images |
| title_fullStr | HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images |
| title_full_unstemmed | HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images |
| title_short | HyTexiLa: High Resolution Visible and Near Infrared Hyperspectral Texture Images |
| title_sort | hytexila high resolution visible and near infrared hyperspectral texture images |
| topic | hyperspectral image spectral analysis effective dimension spectral LBP texture dataset reflectance |
| url | http://www.mdpi.com/1424-8220/18/7/2045 |
| work_keys_str_mv | AT harisahmadkhan hytexilahighresolutionvisibleandnearinfraredhyperspectraltextureimages AT sofianemihoubi hytexilahighresolutionvisibleandnearinfraredhyperspectraltextureimages AT benjaminmathon hytexilahighresolutionvisibleandnearinfraredhyperspectraltextureimages AT jeanbaptistethomas hytexilahighresolutionvisibleandnearinfraredhyperspectraltextureimages AT jonyngvehardeberg hytexilahighresolutionvisibleandnearinfraredhyperspectraltextureimages |