A Supervised Stable Object Detection with Image Feature Extraction using Image Segmentation by Comparing Histogram of Oriented Gradients (HOG) Algorithm over Scale Invariant Feature Transform (SIFT) Algorithm Model.

Abstract

Aim: The objective of the research is to increase the accuracy of object detection using novel image segmentation using machine learning algorithms. Materials and Methods: The categorising is performed by adopting a sample size of n = 10 in Histogram of Oriented Gradients (HOG) and sample size n = 10 in Scale Invariant Feature Transform (SIFT) algorithms with a sample size = 10 and the G-Power analysis was carried out with 80% and confidence interval 95%. Results and Discussion: The analysis of the results shows that the Histogram Of Oriented Gradients (HOG) has a high accuracy of 92.49% in comparison with the Scale Invariant Feature Transform (SIFT) 86.30%. A statistically significant difference exists between the research groups with p=0.001 (2 tailed) (p<0.05). Conclusion: Detection of objects with high accuracy using machine learning algorithms shows that the regional proposal network based Faster R-CNN appears to generate better accuracy than the Selective search(Fast RCNN) algorithm.