期刊
JOURNAL OF ARCHAEOLOGICAL SCIENCE
卷 148, 期 -, 页码 -出版社
ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD
DOI: 10.1016/j.jas.2022.105654
关键词
Phytoliths; Computational archaeology; Deep learning; Machine learning; Google colaboratory
资金
- McDonald Institute for Archaeological Research (Deep Origins: AI Deep Learning ID of Plant Phytoliths) [RYC-2016-19637]
- Spanish Ministry of Science, Innovation and Universities [BOSSS TIN2017-89723-P]
- Spanish Ministry of Science and Innovation
- [EFC-2020-318]
This paper presents an algorithm that automates the detection and classification of multi-cell phytoliths using a deep learning model. With a high overall accuracy, the algorithm shows potential for automatic classification of phytolith genera and species. The open code and platforms used also ensure the accessibility, reproducibility, and reusability of the method.
This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据