• K. Divya Lakshmi Anusha
• Sri. P. Venkateswara Rao

DL base semantic division techniques have been giving best in class execution over the most recent couple of years. All the more explicitly, these procedures have been effectively connected to medical image classification, division, and identification tasks. DL method and U-Net has turned out to be one of the most prominent for these applications. Here an enhancement of existing is RCNN, which names are RU-Net and R2U-Net individually. This models use the intensity of U-Net, Residual Network, just as RCNN. There are a few focal points of enhanced designs for division tasks. Initial, a remaining unit helps when preparing deep design. Second, include collection with repetitive leftover convolution layers guarantees better component portrayal for division tasks. Third, it enables us to configuration heigher U-Net design with equal number of network arguments for better execution. The proposed models are tried on three benchmark datasets, for example, vein division in retina images, skin cancer division, and lung injury division.

"Comparative Analysis on Medical Image Segmentation based on U-Net and Enhanced to R2U-Net", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.747-751, June 2019, Available :http://www.jetir.org/papers/JETIR1907413.pdf

"Comparative Analysis on Medical Image Segmentation based on U-Net and Enhanced to R2U-Net", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp747-751, June 2019, Available at : http://www.jetir.org/papers/JETIR1907413.pdf