Cardiac perfusion magnetic resonance imaging (MRI) has proven clinical significance in diagnosis of heart diseases.
However, analysis of perfusion data is time-consuming, where automatic detection of anatomic landmarks
and key-frames from perfusion MR sequences is helpful for anchoring structures and functional analysis of
the heart, leading toward fully automated perfusion analysis. Learning-based object detection methods have
demonstrated their capabilities to handle large variations of the object by exploring a local region, i.e., context.
Conventional 2D approaches take into account spatial context only. Temporal signals in perfusion data present
a strong cue for anchoring. We propose a joint context model to encode both spatial and temporal evidence. In
addition, our spatial context is constructed not only based on the landmark of interest, but also the landmarks
that are correlated in the neighboring anatomies. A discriminative model is learned through a probabilistic
boosting tree. A marginal space learning strategy is applied to efficiently learn and search in a high dimensional
parameter space. A fully automatic system is developed to simultaneously detect anatomic landmarks and key
frames in both RV and LV from perfusion sequences. The proposed approach was evaluated on a database of
373 cardiac perfusion MRI sequences from 77 patients. Experimental results of a 4-fold cross validation show
superior landmark detection accuracies of the proposed joint spatial-temporal approach to the 2D approach that
is based on spatial context only. The key-frame identification results are promising.
Magnetic resonance imaging (MRI) is currently the gold standard for left ventricle (LV) quantification. Detection of the LV in an MRI image is a prerequisite for functional measurement. However, due to the large variations in orientation, size, shape, and image intensity of the LV, automatic detection of the LV is still a challenging problem. In this paper, we propose to use marginal space learning (MSL) to exploit the recent advances in learning discriminative classifiers. Instead of learning a monolithic classifier directly in the five dimensional object pose space (two dimensions for position, one for orientation, and two for anisotropic scaling) as full space learning (FSL) does, we train three detectors, namely, the position detector, the position-orientation detector, and the position-orientation-scale detector. Comparative experiments show that MSL significantly outperforms FSL in both speed and accuracy. Additionally, we also detect several LV landmarks, such as the LV apex and two annulus points. If we combine the detected candidates from both the whole-object detector and landmark detectors, we can further improve the system robustness. A novel voting based strategy is devised to combine the detected candidates by all detectors. Experiments show component-based voting can reduce the detection
Current two-dimensional image based face recognition systems encounter difficulties with large variations in facial appearance due to the pose, illumination and expression changes. Utilizing 3D information of human faces is promising for handling the pose and lighting variations. While the 3D shape of a face does not change due to head pose (rigid) and lighting changes, it is not invariant to the non-rigid facial movement and evolution, such as expressions and aging effect. We propose a facial surface matching framework to match multiview facial scans to a 3D face model, where the (non-rigid) expression deformation is explicitly modeled for each subject, resulting in a person-specific deformation model. The thin plate spline (TPS) is applied to model the deformation based on the facial landmarks. The deformation is applied to the 3D neutral expression face model to synthesize the corresponding expression. Both the neutral and the synthesized 3D surface models are used to match a test scan. The surface registration and matching between a test scan and a 3D model are achieved by a modified Iterative Closest Point (ICP) algorithm. Preliminary experimental results demonstrate that the proposed expression modeling and recognition-by-synthesis schemes improve the 3D matching accuracy.
Human facial images provide the demographic information, such as ethnicity and gender. Conversely, ethnicity and gender also play an important role in face-related applications. Image-based ethnicity identification problem is addressed in a machine learning framework. The Linear Discriminant Analysis (LDA) based scheme is presented for the two-class (Asian vs. non-Asian) ethnicity classification task. Multiscale analysis is applied to the input facial images. An ensemble framework, which integrates the LDA analysis for the input face images at different scales, is proposed to further improve the classification performance. The product rule is used as the combination strategy in the ensemble. Experimental results based on a face database containing 263 subjects (2,630 face images, with equal balance between the two classes) are promising, indicating that LDA and the proposed ensemble framework have sufficient discriminative power for the ethnicity classification problem. The normalized ethnicity classification scores can be helpful in the facial identity recognition. Useful as a "soft" biometric, face matching scores can be updated based on the output of ethnicity classification module. In other words, ethnicity classifier does not have to be perfect to be useful in practice.