Performance Analysis of Computationally Efficient Model Based Object Detection and Recognition Techniques

Shrddhey Kumar Jain; Supriya O. Rajankar

CALL FOR PAPERS : Feb-2026

Submission Last Date

25-Feb-26

Submit Manuscript Online

FOR AUTHORS

FOR REVIEWERS

ARCHIEVES

DOWNLOADS

Open Access

Performance Analysis of Computationally Efficient Model Based Object Detection and Recognition Techniques

Author(s):

Shrddhey Kumar Jain , Sinhgad College of Engineering, Pune; Supriya O. Rajankar, Sinhgad College of Engineering, Pune

Keywords:

Features from Accelerated Segment Test (FAST) Algorithm, Haar Cascade, Histograms of Oriented Gradient (HOG), Object Detection and Recognition Scale Invariant Feature Transform (SIFT) Algorithm, Speeded-Up Robust Features (SURF) Algorithm, Oriented FAST and Rotated BRIEF (ORB)

Abstract:

Object detection and recognition is one of the vital fields in Machine Learning and Computer Vision. Objects are of innumerable sizes and shapes. The pinnacle of success for any object recognition algorithm is to identify the object that is present in the image or a video sequence irrespective of any parameter like shape, size, color etc. This paper gives a detailed discussion of the computationally efficient object detection and recognition techniques such as Scale Invariant Feature Transform, Speeded-Up Robust Features and Features from Accelerated Segment Test. One more technique, Oriented FAST and rotated BRIEF, is considered as a combination of FAST algorithm along with BRIEF that additionally boasts of properties such as Orientation and rotation invariance. Some techniques which are dedicated for particular type of object such as Haar cascade and Histogram of Oriented Gradients are also glanced briefly upon. The performance parameters accuracy and recognition time are taken into consideration.