Redefining Binarization and the Visual Archetype
This work addresses the definitional and methodological challenges in document image analysis for researchers in computer vision, but it appears incremental as it reframes existing concepts without new empirical results.
The paper tackles the problem of redefining binarization by introducing the concept of a visual archetype as the ideal form for documents, proposing that binarization should be seen as restoring this archetype and shifting ground-truth focus to foreground.
Although binarization is considered passe, it still remains a highly popular research topic. In this paper we propose a rethinking of what binarization is. We introduce the notion of the visual archetype as the ideal form of any one document. Binarization can be defined as the restoration of the visual archetype for a class of images. This definition broadens the scope of what binarization means but also suggests ground-truth should focus on the foreground.