Burn Image Segmentation Based On Mask Regions with Convolutional Neural Network Deep Learning Framework

Authors

  • Prabhakar Kalashetty M.Tech. Student, Department of Computer Science, Sri Satya Sai University of Technology & Medical Sciences, Bhopal, India
  • Gaurave Sexena Professor & HoD, Department of Computer Science, Sri Satya Sai University of Technology & Medical Sciences, Bhopal, India
  • Kailesh Patidar Professor & HoD, Department of Computer Science, Sri Satya Sai University of Technology & Medical Sciences, Bhopal, India

Keywords:

Burning, Effective, Medical

Abstract

Burns are life-threatening and particularly terrible and eternal. The effectiveness of a medical decision and, in some instances, the preservation of a patient's life, involves accurate burn portion evaluation and detailed assessment. Present techniques such as straight-ruling, aseptic movie trimming and digital camera photography cannot be repeated and comparable, which result in a major difference in burn injury assessment and impede the establishment of the same assessment criteria. It makes deep learning technology part of a burns treatment that aims to semi-automatically reduce the detection of Burn and to reduce the impact of human error. This essay aims to use the innovative profound education system as a creative solution to the segmentation of burn wounds. We have created a deep-seated iframe ion from the Mask Regions of the R-CNN. This deep learning method is extremely robust in different depths of burn wound and shows outstanding burn wound segmentation. Therefore, only when examining the burn wound, this structure needs an appropriate burn wound image. In hospitals, it is more accessible and more appropriate than conventional methods. It also applies to burnt total body surface (TBSA) quantities.

Downloads

Download data is not yet available.

Downloads

Published

30-08-2020

Issue

Section

Articles

How to Cite

[1]
P. Kalashetty, G. Sexena, and K. Patidar, “Burn Image Segmentation Based On Mask Regions with Convolutional Neural Network Deep Learning Framework”, IJRESM, vol. 3, no. 8, pp. 478–482, Aug. 2020, Accessed: Jun. 15, 2024. [Online]. Available: https://journal.ijresm.com/index.php/ijresm/article/view/228