Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications
The concept of equifinality is a central issue in taphonomy, conditioning an analyst’s ability to interpret the formation and functionality of palaeontological and archaeological sites. This issue lies primarily in the methods available to identify and characterise microscopic bone surface modificat...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ubiquity Press
2024-12-01
|
| Series: | Journal of Computer Applications in Archaeology |
| Subjects: | |
| Online Access: | https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/145 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554925333512192 |
|---|---|
| author | Lloyd Austin Courtenay Nicolas Vanderesse Luc Doyon Antoine Souron |
| author_facet | Lloyd Austin Courtenay Nicolas Vanderesse Luc Doyon Antoine Souron |
| author_sort | Lloyd Austin Courtenay |
| collection | DOAJ |
| description | The concept of equifinality is a central issue in taphonomy, conditioning an analyst’s ability to interpret the formation and functionality of palaeontological and archaeological sites. This issue lies primarily in the methods available to identify and characterise microscopic bone surface modifications (BSMs) in archaeological sites. Recent years have seen a notable increase in the number of studies proposing the use of deep learning (DL)-based computer vision (CV) algorithms on stereomicroscope images to overcome these issues. Few studies, however, have considered the possible limitations of these techniques. The present research performs a detailed evaluation of the quality of three previously published image datasets of BSMs, replicating the use of DL for the classification of these images. Algorithms are then subjected to rigorous testing. Despite what previous research suggests, DL algorithms are shown to not perform as well when exposed to new data. We additionally conclude that the quality of each of the three datasets is far from ideal for any type of analysis. This raises considerable concerns on the optimistic presentation of DL as a means of overcoming taphonomic equifinality. In light of this, extreme caution is advised until good quality, larger, balanced, datasets, that are more analogous with the fossil record, are available. |
| format | Article |
| id | doaj-art-2f96b7d3411b4ef28bc20a4dfe2cb780 |
| institution | Kabale University |
| issn | 2514-8362 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ubiquity Press |
| record_format | Article |
| series | Journal of Computer Applications in Archaeology |
| spelling | doaj-art-2f96b7d3411b4ef28bc20a4dfe2cb7802025-01-08T07:58:21ZengUbiquity PressJournal of Computer Applications in Archaeology2514-83622024-12-0171388–411388–41110.5334/jcaa.145143Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface ModificationsLloyd Austin Courtenay0https://orcid.org/0000-0002-4810-2001Nicolas Vanderesse1https://orcid.org/0000-0001-8698-8707Luc Doyon2https://orcid.org/0000-0001-7163-6186Antoine Souron3https://orcid.org/0000-0001-7384-4974University of BordeauxUniversity of BordeauxUniversity of BordeauxUniversity of BordeauxThe concept of equifinality is a central issue in taphonomy, conditioning an analyst’s ability to interpret the formation and functionality of palaeontological and archaeological sites. This issue lies primarily in the methods available to identify and characterise microscopic bone surface modifications (BSMs) in archaeological sites. Recent years have seen a notable increase in the number of studies proposing the use of deep learning (DL)-based computer vision (CV) algorithms on stereomicroscope images to overcome these issues. Few studies, however, have considered the possible limitations of these techniques. The present research performs a detailed evaluation of the quality of three previously published image datasets of BSMs, replicating the use of DL for the classification of these images. Algorithms are then subjected to rigorous testing. Despite what previous research suggests, DL algorithms are shown to not perform as well when exposed to new data. We additionally conclude that the quality of each of the three datasets is far from ideal for any type of analysis. This raises considerable concerns on the optimistic presentation of DL as a means of overcoming taphonomic equifinality. In light of this, extreme caution is advised until good quality, larger, balanced, datasets, that are more analogous with the fossil record, are available.https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/145artificial intelligencecomputer visioncut markscarnivoran tooth markstrampling markscrocodylian tooth marks |
| spellingShingle | Lloyd Austin Courtenay Nicolas Vanderesse Luc Doyon Antoine Souron Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications Journal of Computer Applications in Archaeology artificial intelligence computer vision cut marks carnivoran tooth marks trampling marks crocodylian tooth marks |
| title | Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications |
| title_full | Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications |
| title_fullStr | Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications |
| title_full_unstemmed | Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications |
| title_short | Deep Learning-Based Computer Vision Is Not Yet the Answer to Taphonomic Equifinality in Bone Surface Modifications |
| title_sort | deep learning based computer vision is not yet the answer to taphonomic equifinality in bone surface modifications |
| topic | artificial intelligence computer vision cut marks carnivoran tooth marks trampling marks crocodylian tooth marks |
| url | https://account.journal.caa-international.org/index.php/up-j-jcaa/article/view/145 |
| work_keys_str_mv | AT lloydaustincourtenay deeplearningbasedcomputervisionisnotyettheanswertotaphonomicequifinalityinbonesurfacemodifications AT nicolasvanderesse deeplearningbasedcomputervisionisnotyettheanswertotaphonomicequifinalityinbonesurfacemodifications AT lucdoyon deeplearningbasedcomputervisionisnotyettheanswertotaphonomicequifinalityinbonesurfacemodifications AT antoinesouron deeplearningbasedcomputervisionisnotyettheanswertotaphonomicequifinalityinbonesurfacemodifications |