The task of document image segmentation is to represent a digital image in a more interpretable form, recognising regions containing text, background and graphics. This paper presents a peculiar strategy for document image segmentation, where a neuro-fuzzy approach is involved. Firstly, image is segmented into text, graphics or background during a pixel level classification step. Successively, an analysis performed over the obtained regions is devoted to refine the initial segmentation results. A knowledge discovery process is applied to automatically derive from sample data the fuzzy rule bases, responsible of the inference scheme presiding over the classification of image pixels and regions. The proposed method proves to be accurate and robust to page skew and noise.
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo