Vaishnav Kalbhor, Siddhant Mishra, Yash Walke, Prof. Mohandas Pawar
Keywords:
Abstract
Identification of faults/cracks through computer-based techniques is a growing trend these days. Any highly responsive system can be characterized by two key features: quick detection and being highly accurate, by leveraging modern techniques and by efficient utilization of resources.
Bone fracture is the result of an excess external force which is beyond the threshold of the bone. Canny Edge detection is an image processing method used to detect the bone fracture through efficient use of automated fracture detection and it overwhelms the noise removal problem. Nowadays there are several methodologies available for edge detection like: Canny, Log, Prewitt, and Robert. However, these techniques are not useful to detect minor details during analysis due to its inability to perform multiresolution analysis. The other key problem of these techniques is that even though they work fine with high resolution and high-quality images they cannot work as well with noisy images because of their inherent lack of ability to differentiate between edges and the noise components.
The method we are proposing overcomes over these problems using CNN algorithm. The results from the simulations we observed that the proposed method is a better option to perform edge detection at aggregate scales. The method proposed has also proved to be robust enough to extract the necessary information and do the processing needed and handle noise better than the currently available edge detectors.
Article Details
Unique Paper ID: 152183
Publication Volume & Issue: Volume 8, Issue 3
Page(s): 492 - 496
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024