Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

@article{Zhang2006LocalFA,
  title={Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study},
  author={Jianguo Zhang and Marcin Marszalek and Svetlana Lazebnik and Cordelia Schmid},
  journal={International Journal of Computer Vision},
  year={2006},
  volume={73},
  pages={213-238}
}
Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ2 distance. We first evaluate the… 
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study
TLDR
A large-scale evaluation of an approach that represents images as distributions as distributions of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the 2 distance.
Combinations of Feature Descriptors for Texture Image Classification
TLDR
It is demonstrated that using a combination of features improves reliability over using a single feature type when multiple datasets are to be classified, and the importance of selecting the optimal descriptor set and analysis techniques for a given dataset.
Sorted Random Projections for robust texture classification
TLDR
A sorting strategy to a universal yet information-preserving random projection (RP) technique, then comparing two different texture image representations (histograms and signatures) with various kernels in the SVMs yields the best classification rates of which the author is aware.
Spatial Statistics of Visual Keypoints for Texture Recognition
TLDR
A new descriptor of texture images based on the characterization of the spatial patterns of image key-points, formed by cooccurrence statistics of neighboring keypoint pairs for different neighborhood radii is proposed.
Evaluation of local features and classifiers in BOW model for image classification
TLDR
An EMD spatial kernel is proposed to encode the spatial information of local features in the framework of the BOW model and the experimental results show that the proposed kernel outperforms the EMD kernel which does not consider the spatial Information in image classification.
Algorithms and Representations for Visual Recognition
TLDR
This thesis shows that a large number of classifiers used in computer vision that are based on comparison of histograms of low level features, are "additive", and proposes algorithms that enable training and evaluation of additive classifiers that offer better tradeoffs between accuracy, runtime memory and time complexity than previous algorithms.
Using Basic Image Features for Texture Classification
TLDR
This paper investigates the performance of an approach which represents textures as histograms over a visual vocabulary which is defined geometrically, based on the Basic Image Features of Griffin and Lillholm, rather than by clustering.
A Performance Evaluation of Exact and Approximate Match Kernels for Object Recognition
Local features have repeatedly shown their effectiveness for object recognition during the last years, and they have consequently become the preferred descriptor for this type of problems. The
A spatial pyramid approach for texture classification
Texture classification, texture synthesis, or similar tasks are an active topic in computer vision and pattern recognition. This paper aims to present two spatial pyramid representations for texture
Combining sorted random features for texture classification
TLDR
This paper explores the combining of powerful local texture descriptors and the advantages over single descriptors for texture classification and finds that the SVMs combining of SRP features produces outstanding classification results, outperforming the state-of-the-art for CUReT and KTH-TIPS.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 76 REFERENCES
Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study
Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as
Object Class Recognition Using Discriminative Local Features
In this paper, we introduce a scale-invariant feature selection method that learns to recognize and detect object classes from images of natural scenes. The first step of our method consists of
Object categorization via local kernels
TLDR
An algorithm that combines support vector machines with local features via a new class of Mercer kernels allows us to perform scalar products on feature vectors consisting of local descriptors, computed around interest points (like corners), able to recognize multi-object categories in different settings.
Object categorization via local kernels
This paper considers the problem of multi-object categorization. We present an algorithm that combines support vector machines with local features via a new class of Mercer kernels. This class of
Efficient image matching with distributions of local invariant features
  • K. Grauman, Trevor Darrell
  • Mathematics, Computer Science
    2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)
  • 2005
TLDR
This work presents a method for efficiently comparing images based on their discrete distributions of distinctive local invariant features, without clustering descriptors, and evaluates the method with scene, object, and texture recognition tasks.
Pyramid Match Kernels: Discriminative Classification with Sets of Image Features (version 2)
TLDR
A new fast kernel function is presented which maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in this space and is shown to be positive-definite, making it valid for use in learning algorithms whose optimal solutions are guaranteed only for Mercer kernels.
Weak Hypotheses and Boosting for Generic Object Detection and Recognition
TLDR
The first stage of a new learning system for object detection and recognition using Boosting as the underlying learning technique and the inclusion of features from segmented re- gions and even spatial relationships leads us a significant step towards generic object recognition.
The pyramid match kernel: discriminative classification with sets of image features
  • K. Grauman, Trevor Darrell
  • Mathematics, Computer Science
    Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1
  • 2005
TLDR
A new fast kernel function is presented which maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in this space and is shown to be positive-definite, making it valid for use in learning algorithms whose optimal solutions are guaranteed only for Mercer kernels.
Categorizing Nine Visual Classes using Local Appearance Descriptors
TLDR
A thorough evaluation clearly demonstrates that the bag of keypoints method is robust to background clutter and produces good categorization accuracy even without exploiting geometric information.
Improving a Discriminative Approach to Object Recognition Using Image Patches
TLDR
A method that uses image patch histograms and discriminative training to recognize objects in cluttered scenes is substantially improved by adding multi-scale features so that it better accounts for objects of different sizes.
...
1
2
3
4
5
...