A study on classification of mineral pigments based on spectral angle mapper and decision tree

2018 ◽  
Author(s):  
Cheng Fan ◽  
Pengchang Zhang ◽  
Shuang Wang ◽  
Bingliang Hu
Keyword(s):  
Decision Tree ◽  
Spectral Angle Mapper ◽  
Spectral Angle

Contaminant Classification of Poultry Hyperspectral Imagery using a Spectral Angle Mapper Algorithm

2007 ◽  
Vol 96 (3) ◽  
pp. 323-333 ◽  
Author(s):  
B. Park ◽  
W.R. Windham ◽  
K.C. Lawrence ◽  
D.P. Smith
Keyword(s):  
Hyperspectral Imagery ◽  
Spectral Angle Mapper ◽  
Spectral Angle

scholarly journals Spatial Prior Fuzziness Pool-Based Interactive Classification of Hyperspectral Images

2019 ◽  
Vol 11 (9) ◽  
pp. 1136 ◽  
Author(s):  
Muhammad Ahmad ◽  
Asad Khan ◽  
Adil Mehmood Khan ◽  
Manuel Mazzara ◽  
Salvatore Distefano ◽  
...  
Keyword(s):  
Hyperspectral Image ◽  
Sample Selection ◽  
Spectral Angle Mapper ◽  
Classifier Design ◽  
Heterogeneous Samples ◽  
Marginal Probability Distribution ◽  
Benchmark Datasets ◽  
Manual Selection ◽  
Spectral Angle

Acquisition of labeled data for supervised Hyperspectral Image (HSI) classification is expensive in terms of both time and costs. Moreover, manual selection and labeling are often subjective and tend to induce redundancy into the classifier. Active learning (AL) can be a suitable approach for HSI classification as it integrates data acquisition to the classifier design by ranking the unlabeled data to provide advice for the next query that has the highest training utility. However, multiclass AL techniques tend to include redundant samples into the classifier to some extent. This paper addresses such a problem by introducing an AL pipeline which preserves the most representative and spatially heterogeneous samples. The adopted strategy for sample selection utilizes fuzziness to assess the mapping between actual output and the approximated a-posteriori probabilities, computed by a marginal probability distribution based on discriminative random fields. The samples selected in each iteration are then provided to the spectral angle mapper-based objective function to reduce the inter-class redundancy. Experiments on five HSI benchmark datasets confirmed that the proposed Fuzziness and Spectral Angle Mapper (FSAM)-AL pipeline presents competitive results compared to the state-of-the-art sample selection techniques, leading to lower computational requirements.

scholarly journals Forest vegetation assessment using geoinformation tools: a case of the Burla pine forest, Novosibirsk Region, Russia

2018 ◽  
Vol 11 ◽  
pp. 00008
Author(s):  
Tatiyana S. Chernikova ◽  
Yury S. Otmakhov ◽  
Daria D. Daibova
Keyword(s):  
Remote Sensing ◽  
Supervised Classification ◽  
Remote Sensing Data ◽  
Pine Forest ◽  
Spectral Angle Mapper ◽  
Sensing Data ◽  
Classification Technique ◽  
Spectral Angle ◽  
Birch Forests

The paper presents the vegetation thematic classification of the Burla banded pine forest carried on using "Canopus-V" remote sensing data and the supervised classification technique by a spectral angle mapper. Areas of selected elements have been assessed: 1. Pine forests, 2. Birch forests; 3. Meadows; 4. Anthropogenic objects (roads, etc.); 5. Agricultural lands; 6. Water objects. Sites of anthropogenic disturbed forests are identified according to remote sensing data. The results show that the data obtained in the classification by a spectral angle can be used to compile geobotanical maps, but due to low spectral resolution of Canopus-V satellite data, it is not always possible to classify individual objects validlys.

Quantitative mineralogy of chromite ore based on imaging Laser Induced Breakdown Spectroscopy and Spectral Angle Mapper Classification Algorithm

2020 ◽  
Author(s):  
Dieter Rammlmair ◽  
Jeannet Meima
Keyword(s):  
Matrix Effects ◽  
Classification Algorithm ◽  
Heterogeneous Distribution ◽  
Spectral Angle Mapper ◽  
Merensky Reef ◽  
Quantitative Mineralogy ◽  
Laser Induced Breakdown ◽  
Reference Measurements ◽  
Spectral Angle

<p>The chemical, mineralogical and textural investigation of drill cores demands objective and repeatable information unaffected by the human bias to be able to correlate significant features across drillcores. Imaging Laser induced Breakdown Spektroscopy (LIBS) can be applied to large scales at high spatial resolution in relatively short times to obtain detailed chemical, mineralogical and textural information with a minimum of sample preparation. The application of the Spectral Angle Mapper (SAM) algorithm for supervised classification of the LIBS hyperspectral data cubes provides a relatively fast, but easy to handle tool to visualize and quantify variations in the chemical, mineralogical composition of complex ores from the sub-millimetre to the metre scale. The information derived offers novel and barely investigated interpretation opportunities in a very detailed manner which directly can be used for exploration purposes. The investigated Merensky Reef is about 1 m thick. It consists of pegmatoidal pyroxenite framed by the lower and upper thin chromitite seams. The Merensky Reef is one major ore body out of three for platinum-group elements (PGE) within the Bushveld Igneous Complex which is the world’s largest known layered intrusion and largest PGE resource on Earth   Detailed LIBS-based imaging measurements with 200µm spotsize were accompanied by space-resolved reference measurements based on SEM/MLA (4µm) and µ-EDXRF (20µm), as well as bulk chemical analyses for multiple core slices. The SAM algorithm was applied for classification of hyperspectral LIBS images as being sensitive for differences in mineral chemistry. Focus was put on the pre-processing of LIBS spectra prior to SAM classification, on the development of the spectral library, and on the validation of the classified data. The SAM classification algorithm, which is solely based on ratios between spectral intensities, was found insensitive to normal shot-to-shot plasma variations and to chemically induced matrix effects. However, the algorithm may become inaccurate at low signal to noise ratios, at the border between different mineral grains (mixed spectra), or when classifying chemically similar phases such as pyrite and pyrrhotite. The extent of mixed spectra depends both on the size of the mineral grains as well as on the spot size of the LIBS laser. The SAM algorithm was successfully applied for classification of several base metal sulphides, rock-forming minerals, accessory minerals, as well as several mixed phases representing the main borders between different mineral grains. The obtained classified LIBS image images the spatial distribution of the different phases, which corresponds very well to the reference measurements based on highly space-resolved  EDXRF and SEM/MLA mineral distribution maps. The investigated core piece highlights the extremely heterogeneous distribution of e.g. the sulphide phases. The LIBS-SAM classification image was used to estimate metal concentrations based on point counting. The applicability has been explored for Cu, Ni, S, and Cr. This approach, when applied on sufficiently large surfaces, enables quantification of well-defined mineral phases, as well as the possible detection of trace elements (e.g. Pt, Pd) that occur in very small nuggets.</p>

Sign in / Sign up

Export Citation Format

Share Document