Information Technology Reference
In-Depth Information
Fig. 2 Character image samples contributed by a single writer
5 Preprocessing
Preprocessing is done to remove the variability that was present in off-line hand-
written characters. The preprocessing techniques that have been employed in an
attempt
to increase the performance of the recognition process are mentioned
below.
5.1 Grayscale Conversion
The grayscale images are those images in which each pixel carries the intensity
information only. Images of this type are also called black-and-white images and
are composed of many shades of Gray varying from black at the weakest intensity
to the white at the strongest. Grayscale images are also called monochrome images
denoting the presence of only one (mono) color (crome) and are different from the
bi-level binary images having only the two colors Black and White.
In this phase of preprocessing, the input image of handwritten character in BMP
format from the local database as shown in Fig. 3 is converted into grayscale format
by using
method of MATLAB and the resultant handwritten character
image is shown in Fig. 4 . This preprocessing step is necessary so as to overcome the
problems that may arise due to the use of pens of different colors and different
intensities on various noisy and colored backgrounds.
rgb2gray
Search WWH ::




Custom Search