Digital image-based document digitization using a graph model

A computer program product, in particular a computer readable medium, the computer program product carrying computer executable code for execution by a processor controlling an apparatus, wherein execution of the instructions cause the processor to perform a method for digitizing a document, the document having assigned a predetermined classification scheme, the method comprising:

• receiving a digital image, the image representing a portion of the document;
• determining a segmentation of the image into one or more image segments;
• for each of the image segments, capturing content information from the image segment and assigning a category to the image segment, the category being selected from the classification scheme;
• selecting one or more digitization segments from the segmentation;
• and
• populating a graph model of the document, wherein each of the digitization segments is represented by a segment node of the graph model, each segment node comprising the category assigned to the digitization segment represented by the segment node and the content information captured from the digitization segment represented by the segment node.