910 XXXI International Mineral Processing Congress 2024 Proceedings/Washington, DC/Sep 29–Oct 3
the darker blue grains. On the other hand, Quartz has a
brighter blue and semi-transparent appearance.
The EDS has a map scan mode which repeatedly con-
ducts point scans in a raster scan pattern of the specified
region and colour codes the presence of the elements. On
of the particles from table above was map-scanned under
EDS which the results are shown in Figure 6. This par-
ticle was selected to demonstrate and validate the mineral
association detected by MinDet and SEM. The EDS map
scan indicated that there is an iron sulfide in the blue reflec-
tive region of the images collected by MinDet, and from
the XRD analysis we know the only iron sulfide present
is Pyrite. The area is shown by the red line in the image.
At the same time, the lack of sulfide in the brown regions,
surrounded by yellow line, indicates that it is an iron oxide
bearing gangue mineral.
The learnings from comparing the MinDet images
with the SEM and EDS results was then used to identify
and label 5211 particles. The information was used to train
the DL algorithm for quartz, chalcopyrite, pyrite, sphal-
erite, and galena which are the major sulfide and gangue
minerals in the ore (Koh et al., 2024).
Modal Mineralogy—Validation
The detailed methodology for validating the modal min-
eralogy methodology of MinDet can be found in Koh et
al., (2024) and the following section is a summary of the
findings. In the validation process, a new set of samples
were made by mixing concentrate and tail samples at dif-
ferent ratios. After scanning those samples by MinDet, the
images were run through DL and superpixel algorithms
simultaneously to get the sample’s modal mineralogy by
size. An example of the image and results reported by
MinDet is shown in Figure 7. In this image the assump-
tion is all the particles contain one mineral only which is
not usually the case for coarser size fractions. Liberation
degree of minerals reduces as particle size increases until the
particle size become way larger than the mineral grain size.
MinDet software detects the particles and their min-
eralogy in an image and calculated the mineral content by
surface area in that image. The surface content then is con-
verted to elemental by mass assays using the density of the
detected minerals and their mineral composition. To vali-
date the MinDet results only 20 images were taken from
each sample and only the sulfide minerals were detected in
the first attempt. The non detected minerals assume to be
non sulfide gangue at specific gravity of 2.7.
In the first run of validation with 20 images, nine sam-
ples were selected to cover a wide range of mineral grades.
The elemental assay reported by MinDet were compared
to the actual ICP-MS assay results for those samples. The
error values for copper, lead, zinc, and sulfur were 1.3%,
1.5%, 0.26% and 1.74% respectively (Figure 8). Error for
iron was higher (7.18%) due to its existence in some of the
gangue minerals which were not detected.
It was hypothesised the more images analysed by
MinDet can improve the accuracy of the results. Therefore,
three samples were selected which to be scanned five times
with MinDet which are shown as five pass sample results in
Figure 9. The error values for copper, lead, zinc, and sulfur
were significantly reduced to 0.41%, 0.66%, 0.15% and
1.03% respectively for those samples. Error for iron is still
Figure 6. Methodology used in this study which combines SEM and EDS map scans with the MinDet image to identify locked
Pyrite and Iron Oxide bearing gangue
the darker blue grains. On the other hand, Quartz has a
brighter blue and semi-transparent appearance.
The EDS has a map scan mode which repeatedly con-
ducts point scans in a raster scan pattern of the specified
region and colour codes the presence of the elements. On
of the particles from table above was map-scanned under
EDS which the results are shown in Figure 6. This par-
ticle was selected to demonstrate and validate the mineral
association detected by MinDet and SEM. The EDS map
scan indicated that there is an iron sulfide in the blue reflec-
tive region of the images collected by MinDet, and from
the XRD analysis we know the only iron sulfide present
is Pyrite. The area is shown by the red line in the image.
At the same time, the lack of sulfide in the brown regions,
surrounded by yellow line, indicates that it is an iron oxide
bearing gangue mineral.
The learnings from comparing the MinDet images
with the SEM and EDS results was then used to identify
and label 5211 particles. The information was used to train
the DL algorithm for quartz, chalcopyrite, pyrite, sphal-
erite, and galena which are the major sulfide and gangue
minerals in the ore (Koh et al., 2024).
Modal Mineralogy—Validation
The detailed methodology for validating the modal min-
eralogy methodology of MinDet can be found in Koh et
al., (2024) and the following section is a summary of the
findings. In the validation process, a new set of samples
were made by mixing concentrate and tail samples at dif-
ferent ratios. After scanning those samples by MinDet, the
images were run through DL and superpixel algorithms
simultaneously to get the sample’s modal mineralogy by
size. An example of the image and results reported by
MinDet is shown in Figure 7. In this image the assump-
tion is all the particles contain one mineral only which is
not usually the case for coarser size fractions. Liberation
degree of minerals reduces as particle size increases until the
particle size become way larger than the mineral grain size.
MinDet software detects the particles and their min-
eralogy in an image and calculated the mineral content by
surface area in that image. The surface content then is con-
verted to elemental by mass assays using the density of the
detected minerals and their mineral composition. To vali-
date the MinDet results only 20 images were taken from
each sample and only the sulfide minerals were detected in
the first attempt. The non detected minerals assume to be
non sulfide gangue at specific gravity of 2.7.
In the first run of validation with 20 images, nine sam-
ples were selected to cover a wide range of mineral grades.
The elemental assay reported by MinDet were compared
to the actual ICP-MS assay results for those samples. The
error values for copper, lead, zinc, and sulfur were 1.3%,
1.5%, 0.26% and 1.74% respectively (Figure 8). Error for
iron was higher (7.18%) due to its existence in some of the
gangue minerals which were not detected.
It was hypothesised the more images analysed by
MinDet can improve the accuracy of the results. Therefore,
three samples were selected which to be scanned five times
with MinDet which are shown as five pass sample results in
Figure 9. The error values for copper, lead, zinc, and sulfur
were significantly reduced to 0.41%, 0.66%, 0.15% and
1.03% respectively for those samples. Error for iron is still
Figure 6. Methodology used in this study which combines SEM and EDS map scans with the MinDet image to identify locked
Pyrite and Iron Oxide bearing gangue