Local Grayvalue Invariants for Image Retrieval

@article{Schmid1997LocalGI,
  title={Local Grayvalue Invariants for Image Retrieval},
  author={Cordelia Schmid and Roger Mohr},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  year={1997},
  volume={19},
  pages={530-535}
}
  • C. Schmid, R. Mohr
  • Published 1 May 1997
  • Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
This paper addresses the problem of retrieving images from large image databases. The method is based on local grayvalue invariants which are computed at automatically detected interest points. A voting algorithm and semilocal constraints make retrieval possible. Indexing allows for efficient retrieval from a database of more than 1,000 images. Experimental results show correct retrieval in the case of partial visibility, similarity transformations, extraneous features, and small perspective… Expand
Content-Based Image Retrieval Based on Local Affinely Invariant Regions
TLDR
This contribution develops a new technique for content-based image retrieval that classify the images based on local invariants that represent the image in a very compact way and allow fast comparison and feature matching with images in the database. Expand
Image Retrieval using Harris Corners and Histogram of Oriented Gradients
Content based image retrieval is the technique to retrieve similar images from a database that are visually similar to a given query image. It is an active and emerging research field in computerExpand
Image Retrieval Using Visually Significant Points
  • Shanwei Zhao, Ge Wang, Qian Zhao
  • Computer Science
  • 2011 7th International Conference on Wireless Communications, Networking and Mobile Computing
  • 2011
TLDR
A robust and self-adaptive point extraction algorithm based on the block difference of inverse probabilities (BDIP) model is proposed, which provides more significantly retrieval results than the traditional ones. Expand
Image retrieval using VQ-based local gabor feature
A new method of retrieving images from large image databases is proposed. The method is based on vector quantisation (VQ) of local texture information extracted by a Gabor wavelet filter bank atExpand
Invariant content-based image retrieval using a complete set of Fourier-Mellin descriptors
TLDR
The paper presents a complete set of Fourier-Mellin descriptors for object storage and retrieval, and the approach is translation, rotation and scale invariant. Expand
Image retrieval based on local grey-level invariants
During past decades, the enormous growth of image archives has significantly increased the demand for research efforts aimed at efficiently finding specific images within large databases. This paperExpand
Object-based queries using color points of interest
  • Valérie Gouet, N. Boujemaa
  • Computer Science
  • Proceedings IEEE Workshop on Content-Based Access of Image and Video Libraries (CBAIVL 2001)
  • 2001
TLDR
A local image descriptor based on color points of interest is proposed, i.e. points extracted and characterized from a color signal at one go, which is involved in an image indexing and retrieval approach which is dedicated to object or sub-image retrieval. Expand
Color illumination models for image matching and indexing
  • P. Gros
  • Computer Science, Mathematics
  • Proceedings 15th International Conference on Pattern Recognition. ICPR-2000
  • 2000
TLDR
A small abstract about photometry and cameras is presented, which allows one to justify the choice of a color representation system, and a set of color invariants for image matching and indexing are presented. Expand
Local invariant descriptor for image matching
  • Lei Qin, Wei Zeng, W. Gao, Weiqiang Wang
  • Mathematics, Computer Science
  • Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.
  • 2005
TLDR
This paper presents a novel approach for matching two images in the presence of image rotation, scale, and illumination changes based on local invariant features and shows that using this approach results in effective and faster matching. Expand
A Rotation Invariant Image Retrieval with Local Features
TLDR
A method of extracting local texture features from blocks with central interest points detected in an image and a rotation invariant Gabor wavelet filter is proposed and a method of comparing pattern histograms of features classified by VQ (Vector Quanti- zation) among images is proposed. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 63 REFERENCES
Geometric Hashing: A General And Efficient Model-based Recognition Scheme
  • Y. Lamdan, H. Wolfson
  • Computer Science
  • [1988 Proceedings] Second International Conference on Computer Vision
  • 1988
TLDR
A general method for model-based object recognition in occluded scenes is presented based on geometric hashing, which stands out for its efficiency and applications both in 3-D and 2-D. Expand
Object Recognition Using Multidimensional Receptive Field Histograms
TLDR
The mathematical foundations of the technique are described and the results of experiments which compare robustness and recognition rates for different local neighborhood operators and histogram similarity measurements are presented. Expand
The Illumination-Invariant Recognition of 3D Objects Using Local Color Invariants
  • D. Slater, G. Healey
  • Mathematics, Computer Science
  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1996
TLDR
An object recognition system is implemented that indexes into a database of models using the invariants and that uses associated geometric information for hypothesis verification and pose estimation, and is therefore relatively insensitive to occlusion. Expand
Multidimensional Indexing for Recognizing Visual Shapes
TLDR
An analytical framework for studying some properties of model acquisition and recognition techniques based on indexing is introduced and a practical example of high-dimensional global invariants are introduced and used to implement a 2-D shape acquisition/recognition system. Expand
Color Constant Color Indexing
TLDR
Results of tests with the new color-constant-color-indexing algorithm show that it works very well even when the illumination varies spatially in its intensity and color, which circumvents the need for color constancy preprocessing. Expand
Three-dimensional object recognition
TLDR
A precise definition of the 3-D object recognition problem is proposed, basic concepts associated with this problem are discussed, and techniques for obtaining, processing, and characterizing range data are surveyed. Expand
Object Recognition through Invariant Indexing
Introduction 1. Object recognition 2. Plane algebraic projective invariants 3. The recognition architecture: algebraic invariants: LEWIS1 4. Projective invariants of smooth plane curves: LEWIS2 5.Expand
Computing Reeectance Ratios from an Image
This paper presents a photometric invariant called reeectance ratio that can be computed from a single brightness image of a scene. The brightness variation in an image of a surface depends onExpand
Computing reflectance ratios from an image
TLDR
A photometric invariant called reflectance ratio is presented that can be computed from a single brightness image of a scene, which represents a physical property of the region and is invariant to the illumination conditions. Expand
Learning and recognition of 3D objects from appearance
  • H. Murase, S. Nayar
  • Computer Science
  • [1993] Proceedings IEEE Workshop on Qualitative Vision
  • 1993
TLDR
The authors address the problem of automatically learning object models for recognition and pose estimation as one of matching visual appearance rather than shape and present a new compact representation of object appearance that is parameterized by pose and illumination. Expand
...
1
2
3
4
5
...