Morphological Cursive Word Segmentation

This work describes a new algorithm for segmentation of handwritten cursive words, based on the following two hypothesis: 1) there exists natural segmentation points (SPs) corresponding to disconnected characters; and 2) the physical SPs between connected characters are located in ligatures. The morphological operations of opening and closing are utilized in the determination of word ligatures. A genetic algorithm was employed in the search for the optimum structuring element to determine ligatures. 1 Natural segmentation The procedure adopted in this work to determine the existence and location of the natural segmentation points is the analysis of projection histograms taken along five different angles. 2 Ligatures Ligatures are strong candidates to segmentation points in cursive scripts [1].The morphological operations of opening and closing are utilized in the determination of word ligatures. A genetic algorithms (GA) is employed in this work to search for the best structuring elements to determine ligatures in the set of training words. Figure 1 shows the concatenation of two structuring elemennts to form the chromosome for the GA.