Wolf Kienzle

Center-surround patterns emerge as optimal predictors for human saccade targets

The human visual system is foveated, that is, outside the central visual field resolution and acuity drop rapidly. Nonetheless much of a visual scene is perceived after only a few saccadic eye movements, suggesting an effective strategy for selecting saccade targets. It has been known for some time that local image structure at saccade targets influences the selection process. However, the question of what the most relevant visual features are is still under debate. Here we show that center-surround patterns emerge as the optimal solution for predicting saccade targets from their local image structure. The resulting model, a one-layer feed-forward network, is surprisingly simple compared to previously suggested models which assume much more complex computations such as multi-scale processing and multiple feature channels. Nevertheless, our model is equally predictive. Furthermore, our findings are consistent with neurophysiological hardware in the superior colliculus. Bottom-up visual saliency may thus not be computed cortically as has been thought previously.

Automatic detection of preclinical neurodegeneration Presymptomatic Huntington disease

Background: Treatment of neurodegenerative diseases is likely to be most beneficial in the very early, possibly preclinical stages of degeneration. We explored the usefulness of fully automatic structural MRI classification methods for detecting subtle degenerative change. The availability of a definitive genetic test for Huntington disease (HD) provides an excellent metric for judging the performance of such methods in gene mutation carriers who are free of symptoms. Methods: Using the gray matter segment of MRI scans, this study explored the usefulness of a multivariate support vector machine to automatically identify presymptomatic HD gene mutation carriers (PSCs) in the absence of any a priori information. A multicenter data set of 96 PSCs and 95 age- and sex-matched controls was studied. The PSC group was subclassified into three groups based on time from predicted clinical onset, an estimate that is a function of DNA mutation size and age. Results: Subjects with at least a 33% chance of developing unequivocal signs of HD in 5 years were correctly assigned to the PSC group 69% of the time. Accuracy improved to 83% when regions affected by the disease were selected a priori for analysis. Performance was at chance when the probability of developing symptoms in 5 years was less than 10%. Conclusions: Presymptomatic Huntington disease gene mutation carriers close to estimated diagnostic onset were successfully separated from controls on the basis of single anatomic scans, without additional a priori information. Prior information is required to allow separation when degenerative changes are either subtle or variable.

How to find interesting locations in video: a spatiotemporal interest point detector learned from human eye movements

Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful interest points. In this paper we approach the problem by learning a detector from examples: we record eye movements of human subjects watching video sequences and train a neural network to predict which locations are likely to become eye movement targets. We show that our detector outperforms current spatiotemporal interest point architectures on a standard classification dataset.

Automatic 3D face reconstruction from single images or video

This paper presents a fully automated algorithm for reconstructing a textured 3D model of a face from a single photograph or a raw video stream. The algorithm is based on a combination of Support Vector Machines (SVMs) and a Morphable Model of 3D faces. After SVM face detection, individual facial features are detected using a novel regression- and classification-based approach, and probabilistically plausible configurations of features are selected to produce a list of candidates for several facial feature positions. In the next step, the configurations of feature points are evaluated using a novel criterion that is based on a Morphable Model and a combination of linear projections. To make the algorithm robust with respect to head orientation, this process is iterated while the estimate of pose is refined. Finally, the feature points initialize a model-fitting procedure of the Morphable Model. The result is a high resolution 3D surface model.

Learning an Interest Operator from Human Eye Movements

We present an approach for designing interest operators that are based on human eye movement statistics. In contrast to existing methods which use hand-crafted saliency measures, we use machine learning methods to infer an interest operator directly from eye movement data. That way, the operator provides a measure of biologically plausible interestingness. We describe the data collection, training, and evaluation process, and show that our learned saliency measure significantly accounts for human eye movements. Furthermore, we illustrate connections to existing interest operators, and present a multi-scale interest point detector based on the learned function.

Training support vector machines with multiple equality constraints

In this paper we present a primal-dual decomposition algorithm for support vector machine training. As with existing methods that use very small working sets (such as Sequential Minimal Optimization (SMO), Successive Over-Relaxation (SOR) or the Kernel Adatron (KA)), our method scales well, is straightforward to implement, and does not require an external QP solver. Unlike SMO, SOR and KA, the method is applicable to a large number of SVM formulations regardless of the number of equality constraints involved. The effectiveness of our algorithm is demonstrated on a more difficult SVM variant in this respect, namely semi-parametric support vector regression.

Efficient Approximations for Support Vector Machines in Object Detection

We present a new approximation scheme for support vector decision functions in object detection. In the present approach we are building on an existing algorithm where the set of support vectors is replaced by a smaller so-called reduced set of synthetic points. Instead of finding the reduced set via unconstrained optimization, we impose a structural constraint on the synthetic vectors such that the resulting approximation can be evaluated via separable filters. Applications that require scanning an entire image can benefit from this representation: when using separable filters, the average computational complexity for evaluating a reduced set vector on a test patch of size h x w drops from O(h.w) to O(h+w). We show experimental results on handwritten digits and face detection.

Detecting preclinical neurodegeneration: An example from Huntington's disease

MRS prescriptions were placed on confluent WMH when visible. SPECT perfusion data was also acquired on a Phillips triple-head gamma camera. T1 tissue segmentation was performed using a previously published method2. WMH volumes were separately obtained using the program Lesion Explorer 3. Spectral profiles were obtained with the program LCmodel, with concentrations measured relative to creatine4. All images and series were coregistered to T1 space using AIR 5.05. Results: AD subjects showed a negative correlation between relative gray matter volume (GM) and glycerophosphocholineþphosphocholine/creatine (GPC þ PCh/Cr) (r 1⁄4 -0.587,p 1⁄4 0.005) and a positive correlation between GM and glutamateþ glutamine/creatine (Glu þ Gln/Cr) (r 1⁄4 0.538,p 1⁄4 0.012). NC’s showed a positive correlations between normal-appearing-white-matter (NAWM) and both N-acetyl-aspartate/creatine (NAA/Cr) (r 1⁄4 0.423,p 1⁄4 0.035) and GPC þ PCh/Cr (r 1⁄4 0.417,p 1⁄4 0.038). Additionally, SPECT perfusion negatively correlated with relative WMH volume within the MRS sampling voxels (r 1⁄4 -0.585,p 1⁄4 0.007). Conclusions: The presence of a positive relationship between NAA and NAWM in NC’s and the lack thereof in the AD subjects may indicate the comparative health of brain tissues in these groups with the AD group showing greater axonal comprise. The positive relationship between GM volume and Glu þ Gln/Cr in the AD group may reflect neurodegenerative glutamate toxicity. The perfusion correlation shows that the greater the volume of WMH, the greater the decrease in tissue perfusion. MRS can be useful for gaining valuable insight in to metabolic changes taking place in AD and the aging brain. This technique is being extended to a larger sample, and will incorporate diffusion tensor data within the MRS voxels to further understand the disease processes.