Higher order MRF for foreground-background separation in multi-spectral images of historical manuscripts

Abstract

Multi-spectral imaging for the analysis and preservation of ancient documents has gained high attention in recent years. While readability enhancement is based on the multi-spectral image corpus, foreground-background separation still relies mainly on gray level or color images. In this paper we propose a foreground-background separation algorithm designed for multi-spectral images. The main contribution is the simultaneously utilization of spectral and spatial features. While spectral features incorporate the spectral components of the multi-spectral images, the spatial features are based on stroke properties. Higher order Markov Random Fields enables an efficient way to combine both features. To solve higher order energy functions, we introduce a new message update rule in the well known belief propagation algorithm based on a higher order potential function.

MultiSpectral Image Binarization using GMMs

“…Several methods have been proposed for the binarization of multispectral document images: In [9] a higher order MRF is used for the classification of degraded handwritings imaged with a MSI system. Another binarization method [10] combines Independent Component Analysis [11] with an image fusion technique.…”

Neural Networks for Document Image and Text Processing

“…The primary goal is to recover the recto pixels and remove the verso pixels, with the double modeling they could identify recto pixels covered by verso ones. In [Lettner et al 2010] the authors had apply CRFs as well but using MSI as inputs. The model combines spectral and spatial features based on the stroke properties.…”