Deformation Models for Image Recognition

@article{Keysers2007DeformationMF,
  title={Deformation Models for Image Recognition},
  author={Daniel Keysers and Thomas Deselaers and Christian Gollan and H. Ney},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2007},
  volume={29},
  pages={1422-1435}
}
We present the application of different nonlinear image deformation models to the task of image recognition. The deformation models are especially suited for local changes as they often occur in the presence of image object variability. We show that, among the discussed models, there is one approach that combines simplicity of implementation, low-computational complexity, and highly competitive performance across various real-world image recognition tasks. We show experimentally that the model… Expand
Deformations and Discriminative Models for Image Recognition
In this work we present approaches to incorporate domain-knowledge into discriminative classifiers. In particular, we investigate the incorporation of the image distortion model into log-linearExpand
Improving efficiency and effectiveness of the image distortion model
TLDR
The results of the extended IDM have been submitted to the medical automatic annotation task of ImageCLEF 2007 and were ranked in the upper third and the used techniques for reducing the execution time are not limited strictly to IDM but are also applicable to other expensive distance measures. Expand
Invariance analysis of modified C2 features: case study—handwritten digit recognition
TLDR
This study shows that using features proposed by the modified model results in higher handwritten digit recognition rates compared with the original model over English and Farsi handwritten digit datasets, and demonstrates higher invariance of the modified models to various image distortions. Expand
Matching Algorithms for Image Recognition
We analyze the usage of matching algorithms for image recognition. We focus on the approaches which aim at finding nonlinear deformations of an entire image. ZeroOrder Warping (ZOW), Pseudo 2D HiddenExpand
CUDA Implementation of Deformable Pattern Recognition and its Application to MNIST Handwritten Digit Database
TLDR
A deformable pattern recognition method with CUDA implementation using the prototype-parallel displacement computation on CUDA and the gradual prototype elimination technique for reducing the computational time without sacrificing the accuracy. Expand
Performance Study of a Regularization-Based Deformable Handwritten Recognition Approach
TLDR
This study clarifies the accuracy performance of a deformable handwritten recognition approach (DHRA) for digit characters and focuses on several conditions for investigating the accuracy and the sensitivity, that is, the definition of averaging area in regularization process, regularization parameters and the number of k for k-nearest neighborhood method. Expand
AUTOMATIC CLASSIFICATION OF MEDICAL X-RAY IMAGES
TLDR
Experimental results showed the classification performance obtained by exploiting LBP and BoW outperformed the other algorithms with respect to the image representation techniques used. Expand
Deforming the Blurred Shape Model for Shape Description and Recognition
This paper presents a new model for the description and recognition of distorted shapes, where the image is represented by a pixel density distribution based on the Blurred Shape Model combined withExpand
A segmentation-free method for image classification based on pixel-wise matching
TLDR
Two-dimensional continuous dynamic programming (2DCDP) is adopted to optimally capture the corresponding pixels within nonlinearly matched areas in an input image and a reference image representing an object without advance segmentation procedure. Expand
A non-rigid appearance model for shape description and recognition
TLDR
A framework to learn a model of shape variability in a set of patterns based on the Active Appearance Model (AAM) and permits to combine shape deformations with appearance variability is described. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 63 REFERENCES
Statistical Image Object Recognition using Mixture Densities
TLDR
A mixture density based approach to invariant image object recognition, an approach to estimating covariance matrices with respect to image variabilities as well as a new approach to combined classification, called the virtual test sample method are proposed. Expand
Combination of Tangent Vectors and Local Representations for Handwritten Digit Recognition
TLDR
The benefits of this combination of statistical classification using tangent vectors and classification based on local features to improve on the results of the individual approaches are shown bylying it to the well known USPS handwritten digits recognition task. Expand
Local context in non-linear deformation models for handwritten character recognition
TLDR
Starting from a true two-dimensional model, pseudo-two-dimensional and zero-order deformation models are derived that achieve very competitive results across five different tasks, in particular 0.5% error rate on the MNIST task. Expand
A generic approach for image classification based on decision tree ensembles and local sub-windows
TLDR
A comparison with studies from the computer vision literature shows that the method is competitive with the state of the art, an interesting result considering its generality and conceptual simplicity. Expand
Classification of Medical Images using Non-linear Distortion Models
TLDR
Taking into account dependencies within the displacement field of the distortion by using a pseudo two-dimensional hidden Markov model with additional distortion possibilities further improves the error rate. Expand
Experiments with an extended tangent distance
TLDR
An extended tangent distance is incorporated in a kernel density based Bayesian classifier to compensate for affine image variations and an image distortion model for local variations is introduced. Expand
A Survey of Elastic Matching Techniques for Handwritten Character Recognition
TLDR
Elastic matching techniques are classified according to the type of 2DW and the properties of each class are outlined, and several topics around EM, such as the category-dependent deformation tendency of handwritten characters, are discussed. Expand
Pixel-to-Pixel Matching for Image Recognition Using Hungarian Graph Matching
TLDR
An extension of a zero-order matching model called the image distortion model that yields state-of-the-art classification results for different tasks by including the constraint that in the matching process each pixel of both compared images must be matched at least once. Expand
Object recognition from local scale-invariant features
  • D. Lowe
  • Mathematics, 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. Expand
Robust vision-based features and classification schemes for off-line handwritten digit recognition
TLDR
It is shown empirically that the features extracted by the model are linearly separable over a large training set (MNIST) and it is shown that the model is relatively simple yet outperforms other models on the same data set. Expand
...
1
2
3
4
5
...