Abstract

Despite years of work, a robust, widely applicable generic “symmetry detector” that can paral-lel other kinds of computer vision/image processing tools for the more basic structural charac-teristics, such as a “edge” or “corner” detector, remains a computational challenge. A new symmetry feature detector with a descriptor is proposed in this paper, namely the Simple Robust Features (SRF) algorithm. A performance comparison is made among SRF with SRF, Speeded-up Robust Features (SURF) with SURF, Maximally Stable Extremal Regions (MSER) with SURF, Harris with Fast Retina Keypoint (FREAK), Minimum Eigenvalue with FREAK, Features from Accelerated Segment Test (FAST) with FREAK, and Binary Robust Invariant Scalable Keypoints (BRISK) with FREAK. A visual tracking dataset is used in this performance evaluation in terms of accuracy and computational cost. The results have shown that combining the SRF detector with the SRF descriptor is preferable, as it has on average the highest accuracy. Additionally, the computational cost of SRF with SRF is much lower than the others.

Highlights

  • Various feature detectors and descriptors have been developed to solve computer vision problems over the last two decades [1,2]

  • The results have shown that combining the Simple Robust Features (SRF) detector with the SRF descriptor is preferable, as it has on average the highest accuracy

  • Fast Retina Keypoint (FREAK) differs from Binary Robust Invariant Scalable Keypoints (BRISK) in terms of overlapping receptive fields and expoexponential changes in size

Read more

Summary

Introduction

Various feature detectors and descriptors have been developed to solve computer vision problems over the last two decades [1,2]. Performance comparison among feature detectors and descriptors have tional cost It simplifies the process of obtaining feature points without non-maximal supbeen done [16,17]. IntenIt simplifies the process of obtaining featurecan points without non-maximal suppression This algorithm achieve better accuracy with a lower comBesides forming a descriptor matrix with complex calculations, SRF characterizes fea-apputational cost than other existing approaches, which can be implemented in real-life tures according to three aspects: location, grayscale intensity, and gradient intensity with plications, such as surveillance, traffic control, and video communication. This algorithm canjustify achieve accuracy with a lower performance evaluation is done to thebetter performance of SRF with computational other existing alcost than other existing approaches, which can be implemented in real-life applications, gorithms. Performance evaluation is done to justify the performance of SRF with other existing algorithms

Related
Orientation
Harris Detector
Minimum Eigenvalue Detector
The octave layers areare produced byby half-sampling the image in Figure
Proposed Algorithm
Feature Points Detection
Features Description
Feature
Evaluation
Results and and Discussions
Accuracy and Computational
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call