• Corpus ID: 2603372

Locally Uniform Comparison Image Descriptor

@inproceedings{Ziegler2012LocallyUC,
  title={Locally Uniform Comparison Image Descriptor},
  author={Andrew Ziegler and Eric M. Christiansen and David J. Kriegman and Serge J. Belongie},
  booktitle={NIPS},
  year={2012}
}
Keypoint matching between pairs of images using popular descriptors like SIFT or a faster variant called SURF is at the heart of many computer vision algorithms including recognition, mosaicing, and structure from motion. However, SIFT and SURF do not perform well for real-time or mobile applications. As an alternative very fast binary descriptors like BRIEF and related methods use pairwise comparisons of pixel intensities in an image patch. We present an analysis of BRIEF and related… 

Figures and Tables from this paper

A Fast Local Image Descriptor Based on Patch Quantization
TLDR
This paper proposes to use vector quantization (VQ) on local patch descriptor building, offering a novel solution to fast local image representation except for bit test created in BRIEF.
LIPID: Local Image Permutation Interval Descriptor
TLDR
An extensive evaluation on the well-known benchmark datasets reveals the robustness and effectiveness of LIPID as well as its capability to handle illumination changes and texture images.
A Zoned Image Patch Permutation Descriptor
TLDR
In the step of local patch description, intensity permutation and zone division are implemented to construct a novel local image descriptor, with the advantages of inherent robustness and invariance to monotonic brightness changes.
LTD: Local Ternary Descriptor for image matching
TLDR
This paper extends Binary Robust Independent Elementary Features to a Local Ternary Descriptor (LTD), which can deliver more discriminative information than BRIEF while being robust to image deformation.
How many bits do I need for matching local binary descriptors?
TLDR
The interpretation of binary descriptors as a Locality Sensitive Hashing scheme for approximating Kendall's tau rank distance between image patches shows that excellent performance can be achieved using a small fraction of the total number of bits from the whole descriptor, speeding-up matching and reducing storage requirements.
Superpixel-Based Local Features for Image Matching
TLDR
The experimental results show that the proposed efficient extractor and binary descriptor based on superpixels and modified binary robust independent elementary features (BRIEF) descriptor called FSRB can improve the computational efficiency, number of matches, feature distribution and robustness of feature-based image matching.
Full ranking as local descriptor for visual recognition: A comparison of distance metrics on sn
A Performance Analysis of Various Feature Detectors and their Descriptors for Panorama Image Stitching
TLDR
Analysis of the performance of multiple feature detectors and descriptors, namely SIFT, SURF, ORB, BRIEF, BRISK, FREAK, shows that AGAST, FAST and BRISk detectors have the highest number of detected key points, whereas STAR, AKAZE, and MSER have a lower number of extracted key points.
Is There Anything New to Say About SIFT Matching?
TLDR
Experimental evidence shows that, despite their age, SIFT and other hand-crafted descriptors, once enhanced through the proposed strategies, are ready to meet the future image matching challenges.
Local Grouped Invariant Order Pattern for Grayscale-Inversion and Rotation Invariant Texture Classification
TLDR
This paper proposes an image descriptor called local grouped invariant order pattern (LGIOP) for grayscale-inversion and rotation invariant texture classification which jointly encodes neighboring order information and central pixels.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
I-BRIEF: A Fast Feature Point Descriptor with More Robust Features
  • Jie Liu, Xiaohui Liang
  • Computer Science
    2011 Seventh International Conference on Signal Image Technology & Internet-Based Systems
  • 2011
TLDR
This paper replaces the test definition of Binary Robust Independent Elementary Features with a slightly modified one and shows that the modified descriptors are more distinctive and more robust to typical image disturbances such as viewpoint change and image blur that occur in real-world scenarios.
BRISK: Binary Robust invariant scalable keypoints
TLDR
A comprehensive evaluation on benchmark datasets reveals BRISK's adaptive, high quality performance as in state-of-the-art algorithms, albeit at a dramatically lower computational cost (an order of magnitude faster than SURF in cases).
Rank-SIFT: Learning to rank repeatable local interest points
TLDR
Compared with the handcrafted rule-based method used by the standard SIFT algorithm, this algorithm substantially improves the stability of detected local interest point on a very challenging benchmark dataset, in which images were generated under very different imaging conditions.
ORB: An efficient alternative to SIFT or SURF
TLDR
This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.
Speeded-Up Robust Features (SURF)
SIFT-Rank: Ordinal description for invariant feature correspondence
This paper investigates ordinal image description for invariant feature correspondence. Ordinal description is a meta-technique which considers image measurements in terms of their ranks in a sorted
Object recognition from local scale-invariant features
  • D. Lowe
  • Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
TLDR
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
BRIEF: Binary Robust Independent Elementary Features
We propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using
Ordinal Measures for Image Correspondence
  • D. Bhat, S. Nayar
  • Computer Science, Mathematics
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1998
TLDR
These measures serve as a general tool for image matching that are applicable to other vision problems such as motion estimation and texture-based image retrieval and suggest the superiority of ordinal measures over existing techniques under nonideal conditions.
An Intensity-augmented Ordinal Measure for Visual Correspondence
TLDR
A new matching method that improves upon existing methods by using a combination of intensity and rank information and only uncorrelated order changes are considered, which makes the method robust to changes in a single or a few pixels.
...
1
2
3
...