Elements of information theory
Elements of information theory
Using Generative Models for Handwritten Digit Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
GTM: the generative topographic mapping
Neural Computation
Multiresolution tangent distance for affine-invariant classification
NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
IEEE Transactions on Pattern Analysis and Machine Intelligence
Comparing Images Using the Hausdorff Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Transformation-Invariant Clustering Using the EM Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Efficient Pattern Recognition Using a New Transformation Distance
Advances in Neural Information Processing Systems 5, [NIPS Conference]
A bootstrapping algorithm for learning linear models of object classes
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Transformed Component Analysis: Joint Estimation of Spatial Transformations and Image Components
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Model-Based Matching by Linear Combinations of Prototypes
Model-Based Matching by Linear Combinations of Prototypes
Alignment by maximization of mutual information
Alignment by maximization of mutual information
Learning from one example in machine vision by sharing probability densities
Learning from one example in machine vision by sharing probability densities
ICA using spacings estimates of entropy
The Journal of Machine Learning Research
Fast Transformation-Invariant Component Analysis
International Journal of Computer Vision
Proceedings of the 6th Eurographics Symposium on Sketch-Based Interfaces and Modeling
Regression Models of Atlas Appearance
IPMI '09 Proceedings of the 21st International Conference on Information Processing in Medical Imaging
Attribute Vector Guided Groupwise Registration
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part I
Metric Learning for Image Alignment
International Journal of Computer Vision
Non-rigid face tracking with enforced convexity and local appearance consistency constraint
Image and Vision Computing
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
Facial contour labeling via congealing
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Groupwise registration by hierarchical anatomical correspondence detection
MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part II
Sketch recognition by fusion of temporal and image-based features
Pattern Recognition
From engineering diagrams to engineering models: Visual recognition and applications
Computer-Aided Design
Temporal groupwise registration for motion modeling
IPMI'11 Proceedings of the 22nd international conference on Information processing in medical imaging
Technical Section: Neural network-based symbol recognition using a few labeled samples
Computers and Graphics
Style-based retrieval for ancient Syriac manuscripts
Proceedings of the 2011 Workshop on Historical Document Imaging and Processing
Directed graph based image registration
MLMI'11 Proceedings of the Second international conference on Machine learning in medical imaging
Semi-supervised facial landmark annotation
Computer Vision and Image Understanding
Globally Optimal Estimation of Nonrigid Image Distortion
International Journal of Computer Vision
Image registration by normalized mapping
Neurocomputing
Lucas-Kanade based entropy congealing for joint face alignment
Image and Vision Computing
Joint face alignment: rescue bad alignments with good ones by regularized re-fitting
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
Anchored deformable face ensemble alignment
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part I
Feature-based alignment of volumetric multi-modal images
IPMI'13 Proceedings of the 23rd international conference on Information Processing in Medical Imaging
Continuous Generalized Procrustes analysis
Pattern Recognition
Robust gender recognition by exploiting facial attributes dependencies
Pattern Recognition Letters
The Journal of Machine Learning Research
Hi-index | 0.15 |
This paper presents a family of techniques that we call congealing for modeling image classes from data. The idea is to start with a set of images and make them appear as similar as possible by removing variability along the known axes of variation. This technique can be used to eliminate "nuisance” variables such as affine deformations from handwritten digits or unwanted bias fields from magnetic resonance images. In addition to separating and modeling the latent images—i.e., the images without the nuisance variables—we can model the nuisance variables themselves, leading to factorized generative image models. When nuisance variable distributions are shared between classes, one can share the knowledge learned in one task with another task, leading to efficient learning. We demonstrate this process by building a handwritten digit classifier from just a single example of each class. In addition to applications in handwritten character recognition, we describe in detail the application of bias removal from magnetic resonance images. Unlike previous methods, we use a separate, nonparametric model for the intensity values at each pixel. This allows us to leverage the data from the MR images of different patients to remove bias from each other. Only very weak assumptions are made about the distributions of intensity values in the images. In addition to the digit and MR applications, we discuss a number of other uses of congealing and describe experiments about the robustness and consistency of the method.