Abstract
Mineral identification using machine learning requires a significant amount of training data. We built a library of 2D hyperspectral images of minerals. The library contains reflectance images of 130 samples, of 76 distinct minerals, with more than 3.9 million data points. In order to produce this dataset, various well-characterized mineral samples were scanned, using a SPECIM Short Wave Infrared (SWIR) camera, which captures wavelengths from 900 to 2500 nm. Minerals were selected to represent all the mineral classes and the most common mineral occurrences. For each sample, the following data are provided: (a) At least one hyperspectral image of the sample, consisting of 256 wavelengths between 900 and 2500 nm. The raw data, the high dynamic range (HDR) image, and the masked HDR image are provided for each scan (each of them in HDF5 format). (b) A text file describing the sample, providing supplementary information for the subsequent analysis (c) RGB images (JPEG files) and automated 3D reconstructions (Stanford Triangle PLY files). These data help the user to visualize and understand specific sample characteristics. 2D hyperspectral images were produced for each mineral, which consist of many different spectra with high diversity. The scans feature similar spectra than the ones in other available spectral libraries. An artificial neural network was trained to demonstrate the high quality of the dataset. This spectral library is mainly aimed at training machine learning algorithms, such as neural networks, but can be also used as validation data for other types of classification algorithms.
Highlights
Background & SummaryOne of the key applications of hyperspectral imaging is classification
The USGS library was built using high quality spectrometers. This type of measurement provides a single, homogeneized measurement per sample. This type of library is designed for standard classification algorithms such as the spectral angle mapper (SAM) but is not ideal for machine learning algorithms
We use a hyperspectral camera to produce 2D images, which contains many datapoints, contrary to libraries produced by spectrometers
Summary
One of the key applications of hyperspectral imaging is classification. Various algorithms exist to determine mineralogical maps based on hyperspectral images[1]. The USGS library was built using high quality spectrometers This type of measurement provides a single, homogeneized measurement per sample. This type of library is designed for standard classification algorithms such as the SAM but is not ideal for machine learning algorithms. The training dataset should be as diverse as possible, to enable the learning algorithm to generalize as much as possible This new approach requires a new type of spectral library, which contains as much data as possible for each class. We use a hyperspectral camera to produce 2D images, which contains many datapoints, contrary to libraries produced by spectrometers This diversity of the spectra measured is achieved by avoiding homogenization, by measuring mineral samples instead of powders. Minerals were selected from the collection of the University of Neuchâtel, Switzerland, and cover all major mineral classes and of the most commonly occurring minerals[7]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
