Local Enlacement Histograms for Historical Drop Caps Style Recognition

Abstract

This article focuses on the specific issue of drop caps image recognition in the context of cultural heritage preservation. Due to their heterogeneity and their weakly structured properties, these historical images represent challenging data. An important aspect in the recognition process of drop caps is their background styles, which can be considered as discriminative features to identify both the printer and the period. Most existing methods for style recognition are based on low-level features such as color or texture properties. In this article, we present a novel framework for the recognition of drop caps style based on features of higher levels. We propose to capture the spatial structure carried by these images using relative position descriptors modeling the enlacement between local cells of pixel layers obtained from a document segmentation step. Such descriptors are then exploited in an efficient bag-of-features learning procedure. Experimental results obtained on a dataset of historical drop caps images highlight the interest of this approach, and in particular the benefit of considering spatial information.

Enlacement and Interlacement Shape Descriptors

“…The notion of directional spatial enlacement, modeled as an "enlacement" histogram, was initially proposed to assess a new spatial relation between two binary objects [25]. Such a histogram was also embedded in pattern recognition applications considering local features calculated from pairs of broad objects [26]. We show here that it can be easily used to provide a discriminate descriptor (or signature) characterizing only one shape.…”

Fuzzy directional enlacement landscapes for the evaluation of complex spatial relations

“…In this context, recent works [3,29] introduced both enlacement and interlacement descriptors, from the relative position point of view, in order to obtain a robust modeling of these relations for 2D objects. Based on this model, we propose to tackle the dual point of view, by considering fuzzy enlacement landscapes instead of enlacement descriptors.…”