A Neural Approach to Cursive Handwritten Character Recognition Using Features Extracted from Binarization Technique - Complex System Modelling and Control Through Intelligent Soft Computations - page 741

Fig. 8 Handwritten character
image after noise removal

Fig. 9 Cropped handwritten
character image

AND operation of the dilated characters with the pixels removed by '

was performed. The portions of the characters pixels which were very near to the
character image were put back. The resultant image without noise dots while
retaining the portions of the characters is shown in Fig. 8 .

' bwareaopen

5.4 Cropping

Image Cropping is a process in which the extra space around the handwritten
character image is removed. The outcome of method of MATLAB is a

rectangular region with minimum area but containing the complete character image.
The

' imcrop '

final image after cropping operation is shown in Fig. 9 .