Document Layout Analysis (DLA) is a machine vision task that parses a page into meaningful elements, and is a critical stage in Document Understanding (DU). DLA models are usually evaluated with IoU-based metrics such as the F1. However, these metrics are designed for images that are 2D projections of 3D space, not for the natively 2D imagery of printed media. We show both theoretically and empirically that the F1 suffers from two critical failures in the context of DU. These failures are granularity sensitivity, which can lead to F1 collapse even with perfect text extraction; and low semantic competence, which can result in high F1 scores that mask substantial parsing-induced character errors. To remedy these failures we introduce: the Structural Semantic Unit (SSU), a relational labelling approach that shifts the focus from the physical to the semantic structure of the content; and Missing, Overlap, Trespass, and Excess (MOTe) error, a decomposable metric for measuring page parsing error. MOTe correlates more strongly with parsing-induced Character Error Rates (CER) than the F1 (|$ρ$| = 0.82 vs 0.54). MOTe also yields idealised upper and lower bounds on CER that hold in 99% and 82% of model predictions respectively. The lower bound can act as a direct proxy for CER with an $R^2=0.84$. We found that given two models MOTe picks the one that would produce the lowest CER 86% of the time, outperforming pixel-level Dice (77%) and F1 (68%). Finally, we release a Python library for applying MOTe in DLA projects.

翻译：暂无翻译