A neuro-fuzzy technique for document binarisation

Abstract

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. After training, the neurons of the output competition layer of the SOFM define a first approach of the final classes. Using the content of these classes, fuzzy membership functions are obtained that are next used by the fuzzy C-means (FCM) algorithm in order to obtain the colours of the final document. 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.

Self-organizing map-based multi-thresholding on neural stem cells images

“…In the previous work of Papamarkos et al [12,13], Kirsch operators, min and max operators and Laplacian operators were applied to extract features of different kinds of images.…”

“…In order to improve the efficiency of computation as well as represent the original texture better, the Hilbert space-filling curve was selected to sub-sample the original image [12,13]. In this paper, quadtree decomposition, which is widely used in image compression applications [18], was adopted to sub-sample the neural stem cells images.…”

“…Different from the histogram based multi-thresholding methods [16], SOM-based multi-thresholding is essentially a neural network-based classification system on the image features, which can incorporate the local spatial characteristics into the original gray-level image to construct a feature space more than one dimension [13]. This method was applied for binarization of badly illuminated documents [12]; and an adaptive version of SOM was proposed for image multithresholding and segmentation [17].…”

Focused Image Color Quantization using Magnitude Sensitive Competitive Learning Algorithm

“…Celebi presented a relevant work using NG, (Celebi and Schaefer, 2010). SOM has also been used in color related applications: in binarization (Papamarkos, 2003), segmentation (Lazaro et al, 2006 and CQ ( (Dekker, 1994), (Nikolaou and Papamarkos, 2009), (Cheng et al, 2006) and (Chang et al, 2005) where author presents FS-SOM a frequency sensitive learning scheme including neighborhood adaptation that achieves similar results to SOM, but less sensitive to the training parameters. One variant of special interest is the neural network Self-Growing and Self-Organized Neural Gas (SGONG) (Atsalakis and Papamarkos, 2006), a hybrid algorithm using the GNG mechanism for growing the neural lattice and the SOM leaning adaptation mechanism.…”

Document binarisation using Kohonen SOM

“…The most powerful techniques in this category are the logical level technique (LLT) [18] and its improved adaptive logical level technique (ALLT) [19], and the integrated function algorithm technique (IFA) [20] and its advanced 'improvement of integrated function algorithm' (IIFA) [21]. Recently, Papamarkos [22] proposes a new neuro-fuzzy technique for binarisation and grey-level (or colour) reduction of mixed-type documents. In this technique, a neuro-fuzzy classifier is fed by not only the image pixels' values, but also with additional spatial information extracted in the neighbourhood of the pixels.…”