Minimum Description Length Clustering to Measure Meaningful Image Complexity
This work addresses the issue of distinguishing meaningful content from noise in image complexity assessment for computer vision applications, though it appears incremental as it builds on theoretical ideas for measuring complexity.
The authors tackled the problem of existing image complexity metrics incorrectly rating white noise as highly complex by introducing a new metric based on hierarchical clustering of patches and the minimum description length principle, which correctly assigns low scores to white noise and shows accurate scores across seven image sets.
Existing image complexity metrics cannot distinguish meaningful content from noise. This means that white noise images, which contain no meaningful information, are judged as highly complex. We present a new image complexity metric through hierarchical clustering of patches. We use the minimum description length principle to determine the number of clusters and designate certain points as outliers and, hence, correctly assign white noise a low score. The presented method has similarities to theoretical ideas for measuring meaningful complexity. We conduct experiments on seven different sets of images, which show that our method assigns the most accurate scores to all images considered. Additionally, comparing the different levels of the hierarchy of clusters can reveal how complexity manifests at different scales, from local detail to global structure. We then present ablation studies showing the contribution of the components of our method, and that it continues to assign reasonable scores when the inputs are modified in certain ways, including the addition of Gaussian noise and the lowering of the resolution.