Metric Learning for Image Alignment

Discriminative Optimization: Theory and Applications to Computer Vision

Many computer vision problems are formulated as the optimization of a cost function. This approach faces two main challenges: designing a cost function with a local optimum at an acceptable solution, and developing an efficient numerical method to search for this optimum. While designing such functions is feasible in the noiseless case, the stability and location of local optima are mostly unknown under noise, occlusion, or missing data. In practice, this can result in undesirable local optima or not having a local optimum in the expected place. On the other hand, numerical optimization algorithms in high-dimensional spaces are typically local and often rely on expensive first or second order information to guide the search. To overcome these limitations, we propose Discriminative Optimization (DO), a method that learns search directions from data without the need of a cost function. DO explicitly learns a sequence of updates in the search space that leads to stationary points that correspond to the desired solutions. We provide a formal analysis of DO and illustrate its benefits in the problem of 3D registration, camera pose estimation, and image denoising. We show that DO outperformed or matched state-of-the-art algorithms in terms of accuracy, robustness, and computational efficiency.

A Robust Shape Reconstruction Method for Facial Feature Point Detection

Facial feature point detection has been receiving great research advances in recent years. Numerous methods have been developed and applied in practical face analysis systems. However, it is still a quite challenging task because of the large variability in expression and gestures and the existence of occlusions in real-world photo shoot. In this paper, we present a robust sparse reconstruction method for the face alignment problems. Instead of a direct regression between the feature space and the shape space, the concept of shape increment reconstruction is introduced. Moreover, a set of coupled overcomplete dictionaries termed the shape increment dictionary and the local appearance dictionary are learned in a regressive manner to select robust features and fit shape increments. Additionally, to make the learned model more generalized, we select the best matched parameter set through extensive validation tests. Experimental results on three public datasets demonstrate that the proposed method achieves a better robustness over the state-of-the-art methods.

Bayesian Constrained Local Models Revisited

This paper presents a novel Bayesian formulation for aligning faces in unseen images. Our approach revisits the Constrained Local Models (CLM) formulation where an ensemble of local feature detectors are constrained to lie within the subspace spanned by a Point Distribution Model (PDM). Fitting such a model to an image typically involves two main steps: a local search using a detector, obtaining response maps for each landmark (likelihood term) and a global optimization that finds the PDM parameters that jointly maximize all the detections at once. The so-called global optimization can be posed as a Bayesian inference problem, where the posterior distribution of the shape (and pose) parameters can be inferred in a maximum a posteriori (MAP) sense. This work introduces an extended Bayesian global optimization strategy that includes two novel additions: (1) to perform second order updates of the PDM parameters (accounting for their covariance) and (2) to model the underlying dynamics of the shape variations, encoded in the prior term, by using recursive Bayesian estimation. Extensive evaluations were performed against state-of-the-art methods on several standard datasets (IMM, BioID, XM2VTS, LFW and FGNET Talking Face). Results show that the proposed approach significantly increases the fitting performance.

Feature adaptive co-segmentation by complexity awareness

In this paper, we propose a novel feature adaptive co-segmentation method that can learn adaptive features of different image groups for accurate common objects segmentation. We also propose image complexity awareness for adaptive feature learning. In the proposed method, the original images are first ranked according to the image complexities that are measured by superpixel changing cue and object detection cue. Then, the unsupervised segments of the simple images are used to learn the adaptive features, which are achieved using an expectation-minimization algorithm combining l 1-regularized least squares optimization with the consideration of the confidence of the simple image segmentation accuracies and the fitness of the learned model. The error rate of the final co-segmentation is tested by the experiments on different image groups and verified to be lower than the existing state-of-the-art co-segmentation methods.

A general fast registration framework by learning deformation-appearance correlation

In this paper, we propose a general framework for performance improvement of the current state-of-the-art registration algorithms in terms of both accuracy and computation time. The key concept involves rapid prediction of a deformation field for registration initialization, which is achieved by a statistical correlation model learned between image appearances and deformation fields. This allows us to immediately bring a template image as close as possible to a subject image that we need to register. The task of the registration algorithm is hence reduced to estimating small deformation between the subject image and the initially warped template image, i.e., the intermediate template (IT). Specifically, to obtain a good subject-specific initial deformation, support vector regression is utilized to determine the correlation between image appearances and their respective deformation fields. When registering a new subject onto the template, an initial deformation field is first predicted based on the subject's image appearance for generating an IT. With the IT, only the residual deformation needs to be estimated, presenting much less challenge to the existing registration algorithms. Our learning-based framework affords two important advantages: 1) by requiring only the estimation of the residual deformation between the IT and the subject image, the computation time can be greatly reduced; 2) by leveraging good deformation initialization, local minima giving suboptimal solution could be avoided. Our framework has been extensively evaluated using medical images from different sources, and the results indicate that, on top of accuracy improvement, significant registration speedup can be achieved, as compared with the case where no prediction of initial deformation is performed.

Learning a 3D Human Pose Distance Metric from Geometric Pose Descriptor

Estimating 3D pose similarity is a fundamental problem on 3D motion data. Most previous work calculates L2-like distance of joint orientations or coordinates, which does not sufficiently reflect the pose similarity of human perception. In this paper, we present a new pose distance metric. First, we propose a new rich pose feature set called Geometric Pose Descriptor (GPD). GPD is more effective in encoding pose similarity by utilizing features on geometric relations among body parts, as well as temporal information such as velocities and accelerations. Based on GPD, we propose a semisupervised distance metric learning algorithm called Regularized Distance Metric Learning with Sparse Representation (RDSR), which integrates information from both unsupervised data relationship and labels. We apply the proposed pose distance metric to applications of motion transition decision and content-based pose retrieval. Quantitative evaluations demonstrate that our method achieves better results with only a small amount of human labels, showing that the proposed pose distance metric is a promising building block for various 3D-motion related applications.

A machine learning approach for deformable guide-wire tracking in fluoroscopic sequences

Deformable guide-wire tracking in fluoroscopic sequences is a challenging task due to the low signal to noise ratio of the images and the apparent complex motion of the object of interest. Common tracking methods are based on data terms that do not differentiate well between medical tools and anatomic background such as ribs and vertebrae. A data term learned directly from fluoroscopic sequences would be more adapted to the image characteristics and could help to improve tracking. In this work, our contribution is to learn the relationship between features extracted from the original image and the tracking error. By randomly deforming a guide-wire model around its ground truth position in one single reference frame, we explore the space spanned by these features. Therefore, a guide-wire motion distribution model is learned to reduce the intrisic dimensionality of this feature space. Random deformations and the corresponding features can be then automatically generated. In a regression approach, the function mapping this space to the tracking error is learned. The resulting data term is integrated into a tracking framework based on a second-order MAP-MRF formulation which is optimized by QPBO moves yielding high-quality tracking results. Experiments conducted on two fluoroscopic sequences show that our approach is a promising alternative for deformable tracking of guide-wires.