Figure 6c shows the material classification result based on the original spectral reflectance data with the illumination effects.
The material classification experiment results demonstrate that the classification accuracy increases by 10.6%40.8%%, and the fine powder yield increases by 12.5%40.1%%, with an almost changeless cut size.
Unfortunately, this approach results in feature vectors whose dimensionality was too high for the current dataset and yielded poor classification results (Supplementary Material).
The results obtained demonstrate the promising potential of ICAMM for material classification.
Besides problems encountered during the measurement, the interpretation of the results and calculation of the activity indices, needed for material classification, may lead to significant mistakes.
To attach geomorphological meanings to classification results, geometric signatures should be compared with reference materials, and thresholds should be configured after comparison (Iwahashi et al. 2015).
The summary of TAP classification results for (formerly) plastid-bearing organisms (supplementary table 4, Supplementary Material online) enables us to identify trends during the evolution of photosynthetic eukaryotes.
The results shown in Table 3 indicate that the RGB data, as expected, returns the worst performance (43.83%), and better results are obtained when unprocessed (raw) hyper-spectral information is used for material classification (55.67%).
To fully evaluate the performance of the decorrelation methodologies analyzed in this investigation, the results shown in Table 1A, B will be complemented with the results achieved when the data decorrelation algorithms are evaluated in the context of material classification.
PAM50 classification results were downloaded from the UCSC Cancer Genomics Browser [ 39] for TCGA data sets and the supplementary materials in its original publication [ 36] for the EGA data set.
