Skin Cancer Segmentation Using R-CNN Comparing with Inception V3 for Better Accuracy

The major goal of this research is to segment skin cancer novel images more accurately than Inception V3 using R-CNN (Region-based Convolutional Neural Network). In this research work, Skin cancer detection has been carried out using algorithms such as R-CNN and Inception V3 and the accuracy was determined for the same. Two groups are statistically analysed with the sample size 20 for both the groups, with a pretest g power of 80%. The performance of the R-CNN (Region-based Convolutional Neural Network) algorithm is analysed and it is observed that the accuracy is 96.01% and specificity is 86.76 for R-CNN (Region-based Convolutional Neural Network) and 92.00% and specificity is 89.47 for Inception V3 algorithm. The sample size will be computed using the mean, standard deviation, and standard error, as well as the independent samples test if the significance is less than one. According to the statistical study, the two algorithms' accuracy (0.272) and specificity (0.271) significant values are
$\mathbf{p} > 0.05$
. In this research, it was observed that the R-CNN performs more accurately than the Inception V3.