Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Photomicrographs (left) and labels (right).

More »

Fig 1 Expand

Table 1.

Number of images in the train, validation and test sets for each class.

More »

Table 1 Expand

Table 2.

Relative size of regions compared to the image size and number of regions per image.

More »

Table 2 Expand

Fig 2.

Segmentation and classification workflow.

More »

Fig 2 Expand

Table 3.

Model performance in the bone class.

More »

Table 3 Expand

Table 4.

Model performance in the charcoal class.

More »

Table 4 Expand

Table 5.

Model performance in the flint/obsidian class.

More »

Table 5 Expand

Fig 3.

Bone class photomicrograph, ground truth, prediction and comparison of the segmentation, where false positives are shown in green and false negatives in red.

More »

Fig 3 Expand

Fig 4.

Charcoal class photomicrograph, ground truth, prediction and comparison of the segmentation, where false positives are shown in green and false negatives in red.

More »

Fig 4 Expand

Fig 5.

Flint/obsidian class photomicrograph, ground truth, prediction and comparison of the segmentation, where false positives are shown in green and false negatives in red.

More »

Fig 5 Expand

Table 6.

Number and percentage of images per abundance level.

More »

Table 6 Expand

Fig 6.

Confusion matrices of relative abundance classification.

Confusion matrices obtained for the classification of relative abundance using the U-Net model with InceptionV4 as encoder in the test sets for flint/obsidian, charcoal and bone. The categories are: Very Few (<5%), Few (6–15%), Common (16–30%), Frequent (31–50%), Dominant (51–70%), and Very Dominant (>70%).

More »

Fig 6 Expand

Table 7.

Classification performance across abundance categories using U-Net with InceptionV4.

More »

Table 7 Expand