Training Invariant Support Vector Machines
Machine Learning
Motion segmentation and pose recognition with motion history gradients
Machine Vision and Applications - Special issue: IEEE WACV
Robust Real-Time Face Detection
International Journal of Computer Vision
Estimating the Support of a High-Dimensional Distribution
Neural Computation
SIGIR '07 Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval
UPDRS Tests for Diagnosis of Parkinson's Disease Employing Virtual-Touchpad
DEXA '10 Proceedings of the 2010 Workshops on Database and Expert Systems Applications
Computer Methods and Programs in Biomedicine
Special Section on Touching the 3rd Dimension: 3D selection with freehand gesture
Computers and Graphics
Plenoptic cameras in real-time robotics
International Journal of Robotics Research
Journal of Visual Communication and Image Representation
Hi-index | 0.00 |
Objectives: The rapid finger-tapping test (RFT) is an important method for clinical evaluation of movement disorders, including Parkinson's disease (PD). In clinical practice, the naked-eye evaluation of RFT results in a coarse judgment of symptom scores. We introduce a novel computer-vision (CV) method for quantification of tapping symptoms through motion analysis of index-fingers. The method is unique as it utilizes facial features to calibrate tapping amplitude for normalization of distance variation between the camera and subject. Methods: The study involved 387 video footages of RFT recorded from 13 patients diagnosed with advanced PD. Tapping performance in these videos was rated by two clinicians between the symptom severity levels ('0: normal' to '3: severe') using the unified Parkinson's disease rating scale motor examination of finger-tapping (UPDRS-FT). Another set of recordings in this study consisted of 84 videos of RFT recorded from 6 healthy controls. These videos were processed by a CV algorithm that tracks the index-finger motion between the video-frames to produce a tapping time-series. Different features were computed from this time series to estimate speed, amplitude, rhythm and fatigue in tapping. The features were trained in a support vector machine (1) to categorize the patient group between UPDRS-FT symptom severity levels, and (2) to discriminate between PD patients and healthy controls. Results: A new representative feature of tapping rhythm, 'cross-correlation between the normalized peaks' showed strong Guttman correlation (@m"2=-0.80) with the clinical ratings. The classification of tapping features using the support vector machine classifier and 10-fold cross validation categorized the patient samples between UPDRS-FT levels with an accuracy of 88%. The same classification scheme discriminated between RFT samples of healthy controls and PD patients with an accuracy of 95%. Conclusion: The work supports the feasibility of the approach, which is presumed suitable for PD monitoring in the home environment. The system offers advantages over other technologies (e.g. magnetic sensors, accelerometers, etc.) previously developed for objective assessment of tapping symptoms.