Classification of Human Ear Shape with Innovative RF and SVM Machine Learning Algorithms and Related Issues

The main objective of this paper is to improve the accuracy for especial features of ear detection with ear shape images using learning algorithms. Materials and Methods: This paper’s dataset consists of 1416 ear shape images in order to categorise of ear detection. The data are labelled as “ear shape”, “ear size”, “left ear”, “right ear”, image classification from the images into these types, 20 number of images have been used for Random Forest (RF) algorithm taken as case as one and is compared with Support Vector Machine (SVM) algorithm taken as case two with ear shape repository images and it collected in Kaggle website and the parameters are fixed with 95% Confidence Interval and 0.05% significance value. Results: This research study uses two cases of algorithms in this Random Forest (RF) algorithm has achieved an improved accuracy of 98%, compared to the SVM algorithm of 89% and a significant value of 0.028 with a 95% confidence interval. Conclusion: This study discovered that the Random Forest (RF) algorithm predicts ear detection significantly better than the SVM algorithm.