Discovering knowledge through multi-modal association rule mining for document image analysis

The paper introduces a descriptive data mining method to discover knowledge for the task of automatic categorization in document image analysis. We argue that a document image is a multi-modal unit of analysis whose semantics is deduced from a combination of textual content, layout structure and logical structure. So, the method consid-ers simultaneously different modalities of document representation, and, therefore different types of information: spatial information derived from a complex document image analysis process (layout analysis), informa-tion extracted from the logical structure of the document (by means of document image classification and understanding) and the textual infor-mation extracted by means of an OCR. The proposed method is based on a relational data mining approach to discover association rules, where the relational setting is justified, given its appropriateness to analyze data available in more than one modality. Experimental results on a real world dataset are reported.