Abstract
Almost everybody at some point of their life faces the issue of oral cavity. This study aims to identify dental caries in humans, brought on by plaque buildup on the teeth. A thin, sticky coating called dental plaque forms all around the teeth. The primary source of this dental plaque is excessive or frequent consumption of foods high in starch, such as burgers and pizza, also foods high in sugar, such as sweets and chocolates. Cavity forms on teeth when sugar and starch-containing food and beverages are consumed in excess without being thoroughly rinsed from the mouth afterward. Humans should recognize dental caries as soon as they appear on their teeth to prevent them from spreading. Therefore, to identify this caries, we require an algorithm that is quick and adequate to inform us of the state of the teeth/tooth. Residual Neural Network (Resnet50), commonly known as ANN, is the neural network type we use in this research report. Image processing and recognition science have made great strides in recent years. Deep and complex neural networks are developing. It has been that a Neural Network can become more reliable for tasks involving images by adding additional layers to it. However, it might also make them less accurate. We have used the residual neural network in this situation.
Keywords
ANN, Deep Learning, Dental caries detection, Oral cavity, Residual Neural Network, Resnet50.
Citations
IRE Journals:
Ritesh Mourya , Ganesh Patil
"Dental Caries Detection Through Resnet 50 Using Adam Optimizer" Iconic Research And Engineering Journals Volume 7 Issue 8 2024 Page 203-207
IEEE:
Ritesh Mourya , Ganesh Patil
"Dental Caries Detection Through Resnet 50 Using Adam Optimizer" Iconic Research And Engineering Journals, 7(8)
About IRE Journals
IRE Journals is an open access online journals established with an aim to publish high quality of research work in various diciplines. We have more than 6 years in publications. Over 2500+ papers already published.
Important Links
For Authors
Volume 6:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 5:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 4:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12Volume 3:
Issue 1, Issue 2, Issue 3, Issue 4, Issue 5, Issue 6, Issue 7, Issue 8, Issue 9, Issue 10, Issue 11, Issue 12