• P.Kavitha
• Dr.S.Radhimeenakshi

A computer-aided identification system that assists pathologists within the diagnostic method are often therefore effective. Segmentation of blood cells is usually a first step in developing a computer-aided diagnosis system. The segmentation is performed by dividing the complete image into sq. patches that bear a grey level cluster followed by associate reconciling thresholding. Subsequently, the cell labeling is obtained by police investigation the centers of the cells, victimization each distance rework and curvature analysis, and by applying a neighborhood growing method. The benefits of CSC are a unit manifold. The foreground detection method works on grey levels instead of on individual pixels, thus it proves to be terribly economical. Moreover, the mixture of distance rework and curvature analysis makes the numeration method terribly strong to clustered cells. An additional strength of the CSC technique is that the restricted range of parameters that have got to be tuned. Indeed, two completely different versions of the tactic are thought-about, CSC-7 and CSC-3, looking on the amount of parameters to be tuned. The CSC technique has been tested on many in public image datasets of real and artificial pictures.

Keywords: Image Processing, Counting Cells, Cell Labeling, CSC Technique.

"Improved Machine Learning Approach For Microscopic Cell Segmentation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.553-559, June 2019, Available :http://www.jetir.org/papers/JETIR1907R90.pdf

"Improved Machine Learning Approach For Microscopic Cell Segmentation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp553-559, June 2019, Available at : http://www.jetir.org/papers/JETIR1907R90.pdf