Microscopic chromosome analysis, denominated of karyotyping, aims the classification of the chromosomes for assessment of their numeric and structural integrity. In the possibility of this process to be computerized, the cytogeneticists use certain types of image processing softwares, denominated of automatic karyotyping systems. The computerized process presents countless advantages, because it would save the cytogeneticists of the most tireless stage of whole the process. However, these automatic karyotyping systems still present some limitations in the identification of the chromosomes when they are overlapping and/or touching, requiring user intervention to perform this task. The objective of this work is to present the development of a computerized system for cytogenetic analysis and classification trying to overcome such limitations. The system is based on the use of techniques of the fractal geometry theory, through an approach of the Hurst Coefficient method and of the Box-Counting Dimension applied in the stage of extraction of the individual chromosomes characteristics. This may prove to be more precise in the identification and classification of the chromosomes. Due to this work possess multidisciplinary characteristics, the multicriteria methodology was applied for structuring the problem through its several stages.
