A Neuro-Fuzzy Technique For Document Binarisation, Neural Comp. & Appl.
This paper proposes a new neuro-fuzzy technique suitable for binarisation or, in general, the colour reduction of digital documents. The proposed approach uses the image colour values and additional local spatial features extracted in the neighbourhood of the pixels. Both image and local features values feed a Kohonen self-organised feature map (SOFM) neural network classifier. The method can be applied to greyscale and colour documents; it is suitable for improving blurring and badly illuminated documents and can be easily modified to accommodate any type of spatial characteristics.