Improving Optical Myography via Convolutional Neural Networks

In order to improve the accuracy and reliability of myocontrol (control of prosthetic devices using signals gathered from the human body), novel kinds of sensors able to detect muscular activity are being explored. In particular, Optical Myography (OMG) consists of optically tracking and decoding the deformations happening at the surface of the body whenever muscles are activated. OMG potentially requires no devices to be worn, but since it is an advanced problem of computer vision, it incurs a number of other drawbacks, e.g., changing illumination, identification of markers, frame tear and drop. In this work we propose an improvement to OMG as it has been recently introduced, namely we relax the need of precise positioning and orientation of the markers on the body surface. The small size of the markers and their curvature while adhering to the surface of the forearm can lead to missed detections and misdetections in their orientation; here we rather detect the deformations by applying a Convolutional Neural Network to the region of interest around the feature source segmented, from the forearm. The classification-based approach yields results similar to those obtained by other classification based modalities, reaching accuracies in the range of 96.21% to 99.30% when performed on 10 intact subjects.

[1]  Stefano Stramigioli,et al.  Myoelectric forearm prostheses: state of the art from a user-centered perspective. , 2011, Journal of rehabilitation research and development.

[2]  Chee Seng Chan,et al.  A Fusion Approach for Efficient Human Skin Detection , 2012, IEEE Transactions on Industrial Informatics.

[3]  Huzefa Rangwala,et al.  Novel Method for Predicting Dexterous Individual Finger Movements by Imaging Muscle Activity Using a Wearable Ultrasonic System , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[4]  Edwin Olson,et al.  AprilTag: A robust and flexible visual fiducial system , 2011, 2011 IEEE International Conference on Robotics and Automation.

[5]  Carlo Menon,et al.  Force Myography to Control Robotic Upper Extremity Prostheses: A Feasibility Study , 2016, Front. Bioeng. Biotechnol..

[6]  Claudio Castellini,et al.  Optical Myography: Detecting Finger Movements by Looking at the Forearm , 2016, Front. Neurorobot..

[7]  Roberto Merletti,et al.  Advances in surface EMG: recent progress in clinical research applications. , 2010, Critical reviews in biomedical engineering.

[8]  Tarek Abd El-Hafeez A New System for Extracting and Detecting Skin Color Regions from PDF Documents , 2010 .

[9]  S Micera,et al.  Control of Hand Prostheses Using Peripheral Information , 2010, IEEE Reviews in Biomedical Engineering.

[10]  Erik Scheme,et al.  High-density force myography: A possible alternative for upper-limb prosthetic control. , 2016, Journal of rehabilitation research and development.

[11]  Kenneth Sundaraj,et al.  Mechanomyogram for Muscle Function Assessment: A Review , 2013, PloS one.

[12]  Nassir Navab,et al.  OMG: Introducing optical myography as a new human machine interface for hand amputees , 2015, 2015 IEEE International Conference on Rehabilitation Robotics (ICORR).

[13]  G. Naik,et al.  Transradial Amputee Gesture Classification Using an Optimal Number of sEMG Sensors: An Approach Using ICA Clustering , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.