Document image characterization using a multiresolution analysis of the texture: application to old documents

A Pixel Labeling Framework for Comparing Texture Features Application to Digitized Ancient Books

“…In this work, we focus only on textural characteristics. The use of an texture-based approach has been shown to work effectively with skewed and degraded images (Journet et al, 2008).…”

“…Those descriptors will help representing a book page by a hierarchy of homogeneous regions without any hypothesis on the document structure, neither on the document model nor the typographical parameters. In such conditions, a texture analysis technique is a logical choice for solving our problem as it gives several features characterizing the textural properties of a region without using information on the document structure such as the document model and the typographical parameters (Journet et al, 2008).…”

“…the autocorrelation function (Petrou and Sevilla, 2006) and GLCM (Grey Level Co-occurrence Matrix) (Haralick et al, 1973;Busch et al, 2005). The extracted texture features are mainly investigated and analyzed separately in independent experiments for document analysis (Journet et al, 2008). Some works deal with the whole ancient document image (Journet et al, 2008) and others are applied to graphic images such as drop caps (Uttama et al, 2006;Coustaty et al, 2011).…”

“…The extracted texture features are mainly investigated and analyzed separately in independent experiments for document analysis (Journet et al, 2008). Some works deal with the whole ancient document image (Journet et al, 2008) and others are applied to graphic images such as drop caps (Uttama et al, 2006;Coustaty et al, 2011). There have been few comparative studies on gradient, multiple channel Gabor filters, and co-occurrence features (Payne et al, 1994;Said et al, 2000;Liu et al, 2005;Ding et al, 2007;Zhu et al, 2001) for document segmentation, character recognition, and script and language identification.…”

Relational indexing of vectorial primitives for symbol spotting in line-drawing images

“…While in (Sun et al, 2008) a collection of electronic documents are categorized in terms of the presence of a set of watermarks. Finally, in (Journet et al, 2008) the analysis of texture features aim to categorize historical documents. However, since most of these works mainly focus on textual document, they are not applicable when we have to deal with documents containing a large amount of graphical information.…”