||Since 1950, conventional cytology uses glass slides for microscopic analysis of cervical cells, in order to perform Pap Test. Such method yields low-quality images and overlapping cells, which both hampers their analysis and classification. Several countries use a modern method for the realization of Pap test called ThinPrep because it offers high-quality images and overcome the problem of overlapping cells. Our goal is to present a technique for segmenting digital images obtained from conventional cytology method on glass slides. The technique uses Watershed Transform and K-Means Clustering in order to find cell markers or seeds. Nonlinear regression is applied as a way to refine the markers and to allow the Watershed Transform utilization.
Ramon Adrian Salinas Franco received a degree in Engineer in Telematics at the University Distrital Francisco José de Caldas, Bogotá, Colombia, in 2009, a MSc in Science, Technology and Society, University Federal de São Carlos, Brazil, in 2015. He is currently a PhD student at the IMAGElab of Faculty of Technology at University of Campinas, Sao Paulo. His subject is on cervical cancer cell imaging, segmentation, and classification.