Segmentation of Handwritten Numeral Strings in Farsi and English Languages

A new method for segmentation of unconstrained handwritten numeral strings is proposed, and its performance in segmentation of handwritten Farsi and English numeral strings is compared. Our segmentation method uses a combination of features from the foreground and background of the image. In order to find foreground features, an algorithm based on skeleton tracing is introduced for the first time. The skeletons of the connected digits are traversed in clockwise and anticlockwise directions, and intersection points are mapped onto the outer contour to form our foreground features. In order to find background features, another new algorithm is proposed. Considering vertical projections of top and bottom profiles, two background skeletons are found, and feature points are extracted from them. Background and foreground feature points are connected together to construct segmentation paths. Finally each segmentation path is evaluated based on the properties of its left and right connected components. Experiments show our method can provide a list of good segmentation hypotheses for segmentationbased recognition systems. The results of our system are shown on both Farsi and English numeral strings.