Active Learning for Classifying Template Matches in Historical Maps
Active Learning for Classifying Template Matches in Historical Maps
复制标题
用于对历史地图中的模板匹配进行分类的主动学习
DOI：
10.1007/978-3-319-24282-8_5
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Thomas C. van Dijk
中科院分区：
文献类型：
--
作者：
Benedikt Budig;Thomas C. van Dijk
历史地图是各学科学者的重要信息来源。许多图书馆正在将他们的地图集合数字化为位图图像，但是为了使这些集合最有用，需要可搜索的元数据。由于图像的异质性，元数据大多是手工提取的如果有的话：许多集合是如此之大，以至于除了最基本的元数据之外，任何东西都需要不可行的手工工作量。我们提出了一个主动学习的方法，从历史地图中自动提取元数据的实际问题之一：定位出现的图像元素，如文本或地方标记。为此，我们将联合收割机模板匹配（以定位可能发生的事件）与主动学习（以有效地确定分类）相结合。使用这种方法，我们设计了一个人机交互，在地图上的大量元素可以可靠地定位使用很少的用户努力。我们通过实验证明了这种方法对真实世界数据的有效性。
Historical maps are important sources of information for scholars of various disciplines. Many libraries are digitising their map collections as bitmap images, but for these collections to be most useful, there is a need for searchable metadata. Due to the heterogeneity of the images, metadata are mostly extracted by hand—if at all: many collections are so large that anything more than the most rudimentary metadata would require an infeasible amount of manual effort. We propose an active-learning approach to one of the practical problems in automatic metadata extraction from historical maps: locating occurrences of image elements such as text or place markers. For that, we combine template matching (to locate possible occurrences) with active learning (to efficiently determine a classification). Using this approach, we design a human computer interaction in which large numbers of elements on a map can be located reliably using little user effort. We experimentally demonstrate the effectiveness of this approach on real-world data.