Search

Brain Computer Interfaces (BCIs) consist of an interaction between humans and computers with a specific mean of communication, such as voice, gestures, or even brain signals that are usually recorded by an Electroencephalogram (EEG). To ensure an optimal interaction, the BCI algorithm typically involves the classification of the input signals into predefined task-specific categories. However, a recurrent problem is that the classifier can easily be biased by uncontrolled experimental conditions, namely covariates, that are unbalanced across the categories. This issue led to the current solution of forcing the balance of these covariates across the different categories which is time consuming and drastically decreases the dataset diversity. The purpose of this research is to evaluate the need for this forced balance in BCI experiments involving EEG data. A typical design of neural BCIs involves repeated experimental trials using visual stimuli to trigger the so-called Event-Related Potential (ERP). The classifier is expected to learn spatio-temporal patterns specific to categories rather than patterns related to uncontrolled stimulus properties, such as psycho-linguistic variables (e.g., phoneme number, familiarity, and age of acquisition) and image properties (e.g., contrast, compactness, and homogeneity). The challenges are then to know how biased the decision is, which features affect the classification the most, which part of the signal is impacted, and what is the probability to perform neural categorization per se. To address these problems, this research has two main objectives: (1) modeling and quantifying the covariate effects to identify spatio-temporal regions of the EEG allowing maximal classification performance while minimizing the biasing effect, and (2) evaluating the need to balance the covariates across categories when studying brain mechanisms. To solve the modeling problem, we propose using a linear parametric analysis applied to some observable and commonly studied covariates to them. The biasing effect is quantified by comparing the regions highly influenced by the covariates with the regions of high categorical contrast, i.e., parts of the ERP allowing a reliable classification. The need to balance the stimulus's inner properties across categories is evaluated by assessing the separability between category-related and covariate-related evoked responses. The procedure is applied to a visual priming experiment where the images represent items belonging to living or non-living entities. The observed covariates are the commonly controlled psycho-linguistic variables and some visual features of the images. As a result, we identified that the category of the stimulus mostly affects the late evoked response. The covariates, when not modeled, have a biasing effect on the classification, essentially in the early evoked response. This effect increases with the diversity of the dataset and the complexity of the algorithm used. As the effects of both psycho-linguistic variables and image features appear outside of the spatio-temporal regions of significant categorical contrast, the proper selection of the region of interest makes the classification reliable. Having proved that the covariate effects can be separated from the categorical effect, our framework can be further used to isolate the category-dependent evoked response from the rest of the EEG to study neural processes involved when seeing living vs. non-living entities.

The study of eye movements is a common way to non-invasively understand and analyze human behavior. However, eye-tracking techniques are very hard to scale, and require expensive equipment and extensive expertise. In the context of web browsing, these issues could be overcome by studying the link between the eye and the computer mouse. Here, we propose new analysis methods, and a more advanced characterization of this link. To this end, we recorded the eye, mouse, and scroll movements of 151 participants exploring 18 dynamic web pages while performing free viewing and visual search tasks for 20 s. The data revealed significant differences of eye, mouse, and scroll parameters over time which stabilize at the end of exploration. This suggests the existence of a task-independent relationship between eye, mouse, and scroll parameters, which are characterized by two distinct patterns: one common pattern for movement parameters and a second for dwelling/fixation parameters. Within these patterns, mouse and eye movements remained consistent with each other, while the scrolling behaved the opposite way.

With the arrival of low-cost high quality cameras, implicit user behaviour tracking is easier and it becomes very interesting for viewer modelling and content personalization in a TV context. In this paper, we present a comparison between three common algorithms of automatic head direction extraction for a person watching TV in a realistic context. Those algorithms compute the different rotation angles of the head (pitch, roll, yaw) in a non-invasive and continuous way based on 2D and/or 3D features acquired with low cost cameras. These results are compared with a reference based on the Qualisys motion capture commercial system which is a robust marker-based tracking system. The performances of the different algorithms are compared function of different configurations. While our results show that full implicit behaviour tracking in real-life TV setups is still a challenge, with the arrival of next generation sensors (as the new Kinect one sensor), accurate TV personalization based on implicit behaviour is close to become a very interesting option.

This paper presents an analysis system aiming at discriminating between normal and pathological voices. Compared to literature of voice pathology assessment, it is characterised by two aspects. First the system is based on features inspired from voice pathology assessment and music information retrieval. Second the distinction between normal and pathological voices is simply based on the correlation between acoustic features, while more complex classifiers are common in literature. Based on the normal and pathological samples included the MEEI database, it has been found that using two features (spectral decrease and first spectral tristimulus in the Bark scale) and their correlation leads to correct classification rates of 94.7% for pathological voices and 89.5% for normal ones. The system also outputs a normal/pathological factor aiming at giving an indication to the clinician about the location of a subject according to the database.

In the growing market of camera phones, new applications for the visually impaired are nowadays being developed thanks to the increasing capabilities of these equipments. The need to access to text is of primary importance for those people in a society driven by information. To meet this need, our project objective was to develop a multifunctional reading assistant for blind community. The main functionality is the recognition of text in mobile situations but the system can also deal with several specific recognition requests such as banknotes or objects through labels. In this paper, the major challenge is to fully meet user requirements taking into account their disability and some limitations of hardware such as poor resolution, blur, and uneven lighting. For these applications, it is necessary to take a satisfactory picture, which may be challenging for some users. Hence, this point has also been considered by proposing a training tutorial based on image processing methods as well. Developed in a user-centered design, text reading applications are described along with detailed results performed on databases mostly acquired by visually impaired users.

This paper describes a rarity-based visual attention model working on both still images and video sequences. Applications of this kind of models are numerous and we focus on a perceptual image representation which enhances the perceptually important areas and uses lower resolution for perceptually less important regions. Our aim is to provide an approximation of human perception by visualizing its gradual discovery of the visual environment. Comparisons with classical methods for visual attention show that the proposed algorithm is well adapted to anisotropic filtering purposes. Moreover, it has a high ability to preserve perceptually important areas as defects or abnormalities from an important loss of information. High accuracy on low-contrast defects and scalable real-time video compression may be some practical applications of the proposed image representation.