H-Metric: Characterizing Image Datasets via Homogenization Based on KNN-Queries

Precision-Recall is one of the main metrics for evaluating content-based image retrieval techniques. However, it does not provide an ample perception of the properties of an image dataset immerse in a metric space. In this work, we describe an alternative metric named H-Metric, which is determined along a sequence of controlled modifications the image dataset. The process is named homogenization and works by altering the homogeneity characteristics of the classes of images in the dataset. The result is a process that measures how hard it is to deal with a set of images in respect to content-based retrieval, offering support in the task of analyzing distance function-features extractor configurations.