Applying deep learning to right whale photo identification
| Autor: | Marek Cygan, Maciej Klimek, Marcin Mucha, Robert Bogucki, Christin Brangwynne Khan, Jan Kanty Milczek |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0106 biological sciences
卷积神经网络 Computer science algoritmo 01 natural sciences Convolutional neural network Kaggle competition computer vision Photo identification convolutional neural networks redes neurales convolucionales 自动图像识别 education.field_of_study Ecology biology Identification (information) competencia Kaggle machine learning Right whale 机器学习 Conservation of Natural Resources identificación fotográfica Population Kaggle 网站竞赛 Crowdsourcing reconocimiento automatizado de imágenes 010603 evolutionary biology visión computarizada Deep Learning biology.animal aprendizaje automático Animals education automated image recognition Ecology Evolution Behavior and Systematics Nature and Landscape Conservation photo identification algorithm business.industry Whale 010604 marine biology & hydrobiology Deep learning Whales biology.organism_classification Data science Conservation Methods 计算机视觉 照片识别 算法 Artificial intelligence business |
| Zdroj: | Conservation Biology |
| ISSN: | 1523-1739 |
| Popis: | Photo identification is an important tool for estimating abundance and monitoring population trends over time. However, manually matching photographs to known individuals is time‐consuming. Motivated by recent developments in image recognition, we hosted a data science challenge on the crowdsourcing platform Kaggle to automate the identification of endangered North Atlantic right whales (Eubalaena glacialis). The winning solution automatically identified individual whales with 87% accuracy with a series of convolutional neural networks to identify the region of interest on an image, rotate, crop, and create standardized photographs of uniform size and orientation and then identify the correct individual whale from these passport‐like photographs. Recent advances in deep learning coupled with this fully automated workflow have yielded impressive results and have the potential to revolutionize traditional methods for the collection of data on the abundance and distribution of wild populations. Presenting these results to a broad audience should further bridge the gap between the data science and conservation science communities. Article impact statement: Convolutional neural networks identified region, rotated, and cropped images, standardized photos, and identified correctly individual whales. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text