{"references": ["C.Faure and E.Lecolinet. OCR: Handwriting. In R.A.Cole et al, editor,\n\"Survey of the State of the Artin Human Language Technology\", Center\nfor Spoken Language Understanding, Oregon Graduate Institute, pp 86-\n89, 1995.", "W. Senior. \"Off-line handwritten recognition: A review and experiments\".\nTechnical Report CUED/F-INFENG/TR105, Cambridge University Engineering\nDepartment, Dec. 1992.", "C.Higgins and P.Bramall. \"A non-line cursive script recognition system\".\nHandwriting and Drawing Research - Basic and Applied Issues, IOS\nPress, pp. 285-298, 1996.", "R. K. Powalka, N. Sherkat, L. J. Evett and R. J. Whitrow. \"Dynamic cursive\nscript recognition: A hybrid approach\". In Advances in Handwriting\nand Drawing: A multidisciplinary approach, 1994.", "S. Wesolkowski. \"Cursive script recognition: A survey\". Handwriting and\nDrawing Research -Basic and Advanced Issues, IOS Press, pp. 267-284,\n1996.", "R.G. Casey and E. Lecolinet. \"Strategies in character segmentation: A\nsurvey\". Proc. of the 3rd International Conference on Document Analysis\nand Recognition, Montreal, Canada, pp. 1028-1033, 1995.", "K.R. Ayda-zad . C.Z. H s nov. Latin lifbali lyazmalari tanima sisteml\nrind sozl rin seqmentl nm si ucun usul. AMEA XEBERLERI. F.-t.\nv r. elml ri seriyasi. XXVI cild. 3. 2006.", "K.R.Aida-zade, J.Z. Hasanov. \"Handwritten recognition system for azerbaijani\nlatin text\". Proc. of PCI 2008 International conference, pp. xx-yy,\n2008.", "S. Srihari and R.Bozinovic. \"Multi-level perceptron approach to reading\ncursive script\". Artificial Intelligence, vol. 33, pp. 217-255, 1987.\n[10] A.W. Senior. \"Off-line cursive handwritting recognition using recurrent\nneural networks\", Trinity Hall, Cambridge, England, 1994.\n[11] B. Yanikoglu and P. A. Sandon. \"Segmentation of off-line cursive\nhandwriting using linear programming\". Pattern Recognition, Vol. 31,\nNo. 12, pp. 1825-1833, 1998."]}

An approach is offered for more precise definition of base lines- borders in handwritten cursive text and general problems of handwritten text segmentation have also been analyzed. An offered method tries to solve problems arose in handwritten recognition with specific slant or in other words, where the letters of the words are not on the same vertical line. As an informative features, some recognition systems use ascending and descending parts of the letters, found after the word-s baseline detection. In such recognition systems, problems in baseline detection, impacts the quality of the recognition and decreases the rate of the recognition. Despite other methods, here borders are found by small pieces containing segmentation elements and defined as a set of linear functions. In this method, separate borders for top and bottom border lines are found. At the end of the paper, as a result, azerbaijani cursive handwritten texts written in Latin alphabet by different authors has been analyzed.