Abstract
This paper presents three evaluation criteria's for a comparison of two characters segmentation methods for handwritten Arabic words. The first segmentation method is based on a combination between the projection and the minima and maxima of the contour of the image. The second method is a combination between Hough Transform (HT) and Mathematical Morphology (MM) operators. These methods are developed, evaluated and compared with reference to IFN/ENIT-database in comparison of three evaluation criteria's. The first criterion is based on the segments positions (SP). The second criterion is based on the segments numbers (SN). The third is based on the recognition rates by Transparent Neural Network (RR).