Feature extraction is a crucial part of computer vision, which provides visual understanding and analysis of the image. These feature extraction algorithms can be classified on the basis of the type of features extracted or on the basis of the complexity of the algorithm. Scale-Invariant Feature Transform (SIFT) and Oriented Fast and Rotated Brief (ORB) are the most widely used machine learning-based algorithms. SIFT provides scale and rotation-invariant features, while ORB provides efficient real-time computing. This paper presents a unified feature extraction algorithm by combining SIFT and ORB. It uses ORB for efficient key point detection and SIFT for obtaining descriptor computations. Average distance between features and feature extraction time are the performance measures used in our paper. The experimental results show that the combined approach has a satisfactory trade-off in terms of accuracy and computational economy, especially in the case of an oriented image with an average euclidean distance of 623.95.