Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

Automatic distinction of Fernando Pessoas’ heteronyms

Text Mining has opened a vast array of possibilities concerning automatic information retrieval from large amounts of text documents. A variety of themes and types of documents can be easily analyzed. More complex features such as those used in Forensic Linguistics can gather deeper understanding from the documents, making possible performing di cult tasks such as author identi cation. In this work we explore the capabilities of simpler Text Mining approaches to author identification of unstructured documents, in particular the ability to distinguish poetic works from two of Fernando Pessoas' heteronyms: Alvaro de Campos and Ricardo Reis. Several processing options were tested and accuracies of 97% were reached, which encourage further developments.

Development of a semi-automatic self learning pattern recognition system for the control of electronic boards

This project was funded under the Applied Research Grants Scheme administered by Enterprise Ireland. The project was a partnership between Galway - Mayo Institute of Technology and an industrial company, Tyco/Mallinckrodt Galway. The project aimed to develop a semi - automatic, self - learning pattern recognition system capable of detecting defects on the printed circuits boards such as component vacancy, component misalignment, component orientation, component error, and component weld. The research was conducted in three directions: image acquisition, image filtering/recognition and software development. Image acquisition studied the process of forming and digitizing images and some fundamental aspects regarding the human visual perception. The importance of choosing the right camera and illumination system for a certain type of problem has been highlighted. Probably the most important step towards image recognition is image filtering, The filters are used to correct and enhance images in order to prepare them for recognition. Convolution, histogram equalisation, filters based on Boolean mathematics, noise reduction, edge detection, geometrical filters, cross-correlation filters and image compression are some examples of the filters that have been studied and successfully implemented in the software application. The software application developed during the research is customized in order to meet the requirements of the industrial partner. The application is able to analyze pictures, perform the filtering, build libraries, process images and generate log files. It incorporates most of the filters studied and together with the illumination system and the camera it provides a fully integrated framework able to analyze defects on printed circuit boards.

Estimation of nonparametric probability density functions with applications to automatic speech recognition

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2007

Multimodal automatic user disposition recognition in human-machine interaction

Magdeburg, Univ., Fak. für Elektrotechnik und Informationstechnik, Diss., 2013

Automatic top-down processing explains common left occipito-temporal responses to visual words and objects.

Previous studies have demonstrated that a region in the left ventral occipito-temporal (LvOT) cortex is highly selective to the visual forms of written words and objects relative to closely matched visual stimuli. Here, we investigated why LvOT activation is not higher for reading than picture naming even though written words and pictures of objects have grossly different visual forms. To compare neuronal responses for words and pictures within the same LvOT area, we used functional magnetic resonance imaging adaptation and instructed participants to name target stimuli that followed briefly presented masked primes that were either presented in the same stimulus type as the target (word-word, picture-picture) or a different stimulus type (picture-word, word-picture). We found that activation throughout posterior and anterior parts of LvOT was reduced when the prime had the same name/response as the target irrespective of whether the prime-target relationship was within or between stimulus type. As posterior LvOT is a visual form processing area, and there was no visual form similarity between different stimulus types, we suggest that our results indicate automatic top-down influences from pictures to words and words to pictures. This novel perspective motivates further investigation of the functional properties of this intriguing region.

Automatic measurement of key ski jumping phases and temporal events with a wearable system.

We propose a new method, based on inertial sensors, to automatically measure at high frequency the durations of the main phases of ski jumping (i.e. take-off release, take-off, and early flight). The kinematics of the ski jumping movement were recorded by four inertial sensors, attached to the thigh and shank of junior athletes, for 40 jumps performed during indoor conditions and 36 jumps in field conditions. An algorithm was designed to detect temporal events from the recorded signals and to estimate the duration of each phase. These durations were evaluated against a reference camera-based motion capture system and by trainers conducting video observations. The precision for the take-off release and take-off durations (indoor < 39 ms, outdoor = 27 ms) can be considered technically valid for performance assessment. The errors for early flight duration (indoor = 22 ms, outdoor = 119 ms) were comparable to the trainers' variability and should be interpreted with caution. No significant changes in the error were noted between indoor and outdoor conditions, and individual jumping technique did not influence the error of take-off release and take-off. Therefore, the proposed system can provide valuable information for performance evaluation of ski jumpers during training sessions.

Automatic Mallampati Classification Using Active Appearance Models

Difficult tracheal intubation assessment is an important research topic in anesthesia as failed intubations are important causes of mortality in anesthetic practice. The modified Mallampati score is widely used, alone or in conjunction with other criteria, to predict the difficulty of intubation. This work presents an automatic method to assess the modified Mallampati score from an image of a patient with the mouth wide open. For this purpose we propose an active appearance models (AAM) based method and use linear support vector machines (SVM) to select a subset of relevant features obtained using the AAM. This feature selection step proves to be essential as it improves drastically the performance of classification, which is obtained using SVM with RBF kernel and majority voting. We test our method on images of 100 patients undergoing elective surgery and achieve 97.9% accuracy in the leave-one-out crossvalidation test and provide a key element to an automatic difficult intubation assessment system.

The Relative Efficiency of Automatic and Discretionary Industrial Aid

For the last two decades, the primary instruments for UK regional policy have been discretionary subsidies. Such aid is targeted at “additional” projects - projects that would not have been implemented without the subsidy - and the subsidy should be the minimum necessary for the project to proceed. Discretionary subsidies are thought to be more efficient than automatic subsidies, where many of the aided projects are non-additional and all projects receive the same subsidy rate. The present paper builds on Swales (1995) and Wren (2007a) to compare three subsidy schemes: an automatic scheme and two types of discretionary scheme, one with accurate appraisal and the other with appraisal error. These schemes are assessed on their expected welfare impacts. The particular focus is the reduction in welfare gain imposed by the interaction of appraisal error and the requirements for accountability. This is substantial and difficult to detect with conventional evaluation techniques.

Joint estimates of automatic and discretionary fiscal policy for the OECD

Official calculations of automatic stabilizers are seriously flawed since they rest on the assumption that the only element of social spending that reacts automatically to the cycle is unemployment compensation. This puts into question many estimates of discretionary fiscal policy. In response, we propose a simultaneous estimate of automatic and discretionary fiscal policy. This leads us, quite naturally, to a tripartite decomposition of the budget balance between revenues, social spending and other spending as a bare minimum. Our headline results for a panel of 20 OECD countries in 1981-2003 are .59 automatic stabilization in percentage-points of primary surplus balances. All of this stabilization remains following discretionary responses during contractions, but arguably only about 3/5 of it remains so in expansions while discretionary behavior cancels the rest. We pay a lot of attention to the impact of the Maastricht Treaty and the SGP on the EU members of our sample and to real time data.

Joint estimates of automatic and discretionary fiscal policy: the OECD 1981-2003

Official calculations of automatic stabilizers are seriously flawed since they rest on the assumption that the only element of social spending that reacts automatically to the cycle is unemployment compensation. This puts into question many estimates of discretionary fiscal policy. In response, we propose a simultaneous estimate of automatic and discretionary fiscal policy. This leads us, quite naturally, to a tripartite decomposition of the budget balance between revenues, social spending and other spending as a bare minimum. Our headline results for a panel of 20 OECD countries in 1981-2003 are .59 automatic stabilization in percentage-points of primary surplus balances. All of this stabilization remains following discretionary responses during contractions, but arguably only about 3/5 of it remains so in expansions while discretionary behavior cancels the rest. We pay a lot of attention to the impact of the Maastricht Treaty and the SGP on the EU members of our sample and to real time data.

Joint estimates of automatic and discretionary fiscal policy: the OECD 1981-2003

Official calculations of automatic stabilizers are seriously flawed since they rest on the assumption that the only element of social spending that reacts automatically to the cycle is unemployment compensation. This puts into question many estimates of discretionary fiscal policy. In response, we propose a simultaneous estimate of automatic and discretionary fiscal policy. This leads us, quite naturally, to a tripartite decomposition of the budget balance between revenues, social spending and other spending as a bare minimum. Our headline results for a panel of 20 OECD countries in 1981-2003 are .59 automatic stabilization in percentage-points of primary surplus balances. All of this stabilization remains following discretionary responses during contractions, but arguably only about 3/5 of it remains so in expansions while discretionary behavior cancels the rest. We pay a lot of attention to the impact of the Maastricht Treaty and the SGP on the EU members of our sample and to real time data.

Intraobserver and interobserver variability of ascending aorta diameter measurements as assessed by ECG-gated MDCT : automatic versus manual measurements : P15

Purpose: Revolutionary endovascular treatments are on the verge of being available for management of ascending aortic diseases. Morphometric measurements of the ascending aorta have already been done with ECG-gated MDCT to help such therapeutic development. However the reliability of these measurements remains unknown. The objective of this work was to compare the intraobserver and interobserver variability of CAD (computer aided diagnosis) versus manual measurements in the ascending aorta. Methods and materials: Twenty-six consecutive patients referred for ECG-gated CT thoracic angiography (64-row CT scanner) were evaluated. Measurements of the maximum and minimum ascending aorta diameters at mid-distance between the brachiocephalic artery and the aortic valve were obtained automatically with a commercially available CAD and manually by two observers separately. Both observers repeated the measurements during a different session at least one month after the first measurements. Intraclass coefficients as well the Bland and Altman method were used for comparison between measurements. Two-paired t-test was used to determine the significance of intraobserver and interobserver differences (alpha = 0.05). Results: There is a significant difference between CAD and manual measurements in the maximum diameter (p = 0.004) for the first observer, whereas the difference was significant for minimum diameter between the second observer and the CAD (p <0.001). Interobserver variability showed a weak agreement when measurements were done manually. Intraobserver variability was lower with the CAD compared to the manual measurements (limits of variability: from -0.7 to 0.9 mm for the former and from -1.2 to 1.3 mm for the latter). Conclusion: In order to improve reproductibility of measurements whenever needed, pre- and post-therapeutic management of the ascending aorta may benefit from follow-up done by a unique observer with the help of CAD.

Automatic front-crawl temporal phase detection using adaptive filtering of inertial signals

This study introduces a novel approach for automatic temporal phase detection and inter-arm coordination estimation in front-crawl swimming using inertial measurement units (IMUs). We examined the validity of our method by comparison against a video-based system. Three waterproofed IMUs (composed of 3D accelerometer, 3D gyroscope) were placed on both forearms and the sacrum of the swimmer. We used two underwater video cameras in side and frontal views as our reference system. Two independent operators performed the video analysis. To test our methodology, seven well-trained swimmers performed three 300 m trials in a 50 m indoor pool. Each trial was in a different coordination mode quantified by the index of coordination. We detected different phases of the arm stroke by employing orientation estimation techniques and a new adaptive change detection algorithm on inertial signals. The difference of 0.2 +/- 3.9% between our estimation and video-based system in assessment of the index of coordination was comparable to experienced operators' difference (1.1 +/- 3.6%). The 95% limits of agreement of the difference between the two systems in estimation of the temporal phases were always less than 7.9% of the cycle duration. The inertial system offers an automatic easy-to-use system with timely feedback for the study of swimming.