Estimating False Positive Contamination in Crater Annotations from Citizen Science Data

详细信息    查看全文

• 作者：P. D. Tar ; R. Bugiolacchi ; N. A. Thacker ; J. D. Gilmour
• 关键词：Linear Poisson Models ; Moon Zoo ; Citizen science
• 刊名：Earth, Moon, and Planets
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：119
• 期：2-3
• 页码：47-63
• 全文大小：1233KB
• 刊物类别：Physics and Astronomy
• 刊物主题：Astronomy, Observations and Techniques; Planetology; Space Sciences (including Extraterrestrial Physics, Space Exploration and Astronautics); Astrophysics and Astroparticles;
• 出版者：Springer Netherlands
• ISSN：1573-0794
• 卷排序：119

文摘

Web-based citizen science often involves the classification of image features by large numbers of minimally trained volunteers, such as the identification of lunar impact craters under the Moon Zoo project. Whilst such approaches facilitate the analysis of large image data sets, the inexperience of users and ambiguity in image content can lead to contamination from false positive identifications. We give an approach, using Linear Poisson Models and image template matching, that can quantify levels of false positive contamination in citizen science Moon Zoo crater annotations. Linear Poisson Models are a form of machine learning which supports predictive error modelling and goodness-of-fits, unlike most alternative machine learning methods. The proposed supervised learning system can reduce the variability in crater counts whilst providing predictive error assessments of estimated quantities of remaining true verses false annotations. In an area of research influenced by human subjectivity, the proposed method provides a level of objectivity through the utilisation of image evidence, guided by candidate crater identifications.