Hernán F. García

Driving fatigue detection using active shape models

Driver fatigue is a major cause of traffic accidents. The fatigue detection systems based on computer vision have great potential given its property of non-invasiveness. Major challenges that arise are fast movements of eyes and mouth, changes in pose and lighting variations. In this paper an Active Shape Model is presented for facial features detection of features extracted from the parametric model Candide-3. We describe the characterization methodology from parametric model. Also quantitatively evaluated the accuracy for feature detection and estimation of the parameters associated with fatigue, analyzing its robustness to variations in pose and local variations in the regions of interest. The model used and characterization methodology showed efficient to detect fatigue in 100% of the cases.

Peripheral Nerve Segmentation Using Speckle Removal and Bayesian Shape Models

In the field of medicine, ultrasound images have become a useful tool for visualizing nerve structures in the process of anesthesiology. Although, these images are commonly used in medical procedures such as peripheral nerve blocks. Their poor intelligibility makes it difficult for the anesthesiologists to perform this process accurately. Therefore, an automated segmentation methodology of the peripheral nerves can assist the experts in improving accuracy. This paper proposes a peripheral nerve segmentation method in medical ultrasound images, based on Speckle removal and Bayesian shape models. The method allows segmenting efficiently a given nerve by performing a Bayesian shape fitting. The experimental results show that performing a speckle removal before fitting the model, improves the accuracy due to the enhancement of the image to segment.

Dynamic physiological signal analysis based on Fisher kernels for emotion recognition

Emotional behavior is an active area of study in the fields of neuroscience and affective computing. This field has the fundamental role of emotion recognition in the maintenance of physical and mental health. Valence/Arousal levels are two orthogonal, independent dimensions of any emotional stimulus and allows an analysis framework in affective research. In this paper we present our framework for emotional regression based on machine learning techniques. Autoregressive coefficients and hidden markov models on physiological signals, based on Fisher Kernels characterization are presented for mapping variable length sequences to new dimension feature vector space. Then, support vector regression is performed over the Fisher Scores for emotional recognition. Also quantitatively we evaluated the accuracy of the proposed model by acomplishing a hold-out cross validation over the dataset. The experimental results show that the proposed model can effectively perform the regression in comparison with static characterization methods.

Discriminative Training for Convolved Multiple-Output Gaussian Processes

Multi-output Gaussian processes (MOGP) are probability distributions over vector-valued functions, and have been previously used for multi-output regression and for multi-class classification. A less explored facet of the multi-output Gaussian process is that it can be used as a generative model for vector-valued random fields in the context of pattern recognition. As a generative model, the multi-output GP is able to handle vector-valued functions with continuous inputs, as opposed, for example, to hidden Markov models. It also offers the ability to model multivariate random functions with high dimensional inputs. In this paper, we use a discriminative training criteria known as Minimum Classification Error to fit the parameters of a multi-output Gaussian process. We compare the performance of generative training and discriminative training of MOGP in subject recognition, activity recognition, and face recognition. We also compare the proposed methodology against hidden Markov models trained in a generative and in a discriminative way.

Bayesian Shape Models with Shape Priors for MRI Brain Segmentation

Planning a deep brain stimulation surgery in Parkinson disease is a critical task because the medical team needs to accurately locate the basal ganglia area (i.e. sub-thalamus) in a magnetic resonance image study. This paper proposes a new method for shape prior information based on the Chan-Vese model and Bayesian shape models for brain structure segmentation on magnetic resonance images. The method allows to initialize efficiently a given shape by fitting an active contour (Chan-Vese model), and then robustly fits a brain structure, performing a Bayesian shape fitting. The experimental results show that the proposed model can effectively segment a brain structure. Also, the proposed model, provides a fast segmentation which improves the computational cost compared with common segmentation techniques such as active shape models.

Gaussian Process Dynamical Models for Emotion Recognition

We describe a method for dynamic emotion recognition from facial expression sequences. Our model is based on learning a latent space using the Gaussian Process Latent Variable Model (GP-LVM), encapsulating facial landmarks shapes which describe a given facial expression. We incorporate the dynamic model by learning the latent representation, with the aim to respect the data’s dynamics (facial shapes should maintain their correspondence along time). Then, a Gaussian process classifier is implemented to evaluate the relevance of the latent space features in the emotion recognition task. The results show that the proposed method can efficiently model a dynamic facial emotion and recognize with high accuracy a facial emotion sequence.

Dynamic facial landmarking selection for emotion recognition using Gaussian processes

Facial features are the basis for the emotion recognition process and are widely used in affective computing systems. This emotional process is produced by a dynamic change in the physiological signals and the visual answers related to the facial expressions. An important factor in this process, relies on the shape information of a facial expression, represented as dynamically changing facial landmarks. In this paper we present a framework for dynamic facial landmarking selection based on facial expression analysis using Gaussian Processes. We perform facial features tracking, based on Active Appearance Models for facial landmarking detection, and then use Gaussian process ranking over the dynamic emotional sequences with the aim to establish which landmarks are more relevant for emotional multivariate time-series recognition. The experimental results show that Gaussian Processes can effectively fit to an emotional time-series and the ranking process with log-likelihoods finds the best landmarks (mouth and eyebrows regions) that represent a given facial expression sequence. Finally, we use the best ranked landmarks in emotion recognition tasks obtaining accurate performances for acted and spontaneous scenarios of emotional datasets.

Gaussian process dynamical models for multimodal affect recognition

Affective computing systems has a great potential in applications for biofeedback systems and cognitive conductual therapies. Here, by analyzing the physiological behavior of a given subject, we can infer the affective state of an emotional process. Since, emotions can be modeled as dynamic manifestations of these signals, a continuous analysis in the valence/arousal space, brings more information of the affective state related to an emotional process. In this paper we propose a method for dynamic affect recognition from multimodal physiological signals. Our model is based on learning a latent space using Gaussian process latent variable models (GP-LVM), which maps high dimensional data (multimodal physiological signals) in a low dimensional latent space. We incorporate the dynamics to the model by learning the latent representation, with associated dynamics. Finally, a support vector classifier is implemented to evaluate the relevance of the latent space features in the affective recognition process. The results show that the proposed method can efficiently model a physiological time-series and recognize with high accuracy an affective process.

A Kernel-Based Approach for DBS Parameter Estimation

The volume of tissue activated (VTA) is commonly used as a tool to explain the effects of deep brain stimulation (DBS). The VTA allows visualizing the anatomically accurate reconstructions of the brain structures surrounding the DBS electrode as a 3D high-dimensional activate/non-activate image, which leads to important clinical applications, e.g., Parkinson’s disease treatments. However, fixing the DBS parameters is not a straightforward task as it depends mainly on both the specialist expertise and the tissue properties. Here, we introduce a kernel-based approach to learn the DBS parameters from VTA data. Our methodology employs a kernel-based eigendecomposition from pair-wise Hamming distances to extract relevant VTA patterns into a low-dimensional space. Further, DBS parameters estimation is carried out by employing a kernel-based multi-output regression and classification. The presented approach is tested under both isotropic and anisotropic conditions to validate its performance under realistic clinical environments. Obtained results show a significant reduction of the input VTA dimensionality after applying our scheme, which ensures suitable DBS parameters estimation accuracies and avoids over-fitting.

Bayesian optimization for fitting 3D morphable models of brain structures

Localize target areas in deep brain stimulation is a difficult task, due to the shape variability that brain structures exhibit between patients. The main problem in this process is that the fitting procedure is carried out by a registration method that lacks of accuracy. In this paper we proposed a novel method for 3D brain structure fitting based on Bayesian optimization. We use a morphable model in order to capture the shape variability in a given set of brain structures. Then from the trained model, we perform a Bayesian optimization task with the aim to find the best shape parameters that deform the trained model, and fits accurately to a given brain structure. The experimental results show that by using an optimization framework based on Bayesian optimization, the model performs an accurate fitting over cortical brain structures (thalamus, amygdala and ventricle) in comparison with common fitting methods, such as iterative closest point.