Techniques based on computer vision are popular. Subsequent feature selection established the all-pairs amplitude ratios and certain bands of the FFT to be the most predictive features. When shot with a high- speed camera, these appear as ripples, which propagate outward from the point of contact see video. Our software uses the implementation provided in the Weka machine learning toolkit. Before the SVM can classify input instances, it must first be trained to the user and the sensor position. Appropriating the Body as an Input Surface Devices with significant computational power and capabilities can now be easily carried on our bodies.
As such, we found them to be lacking in several significant ways. This suggests there are only limited acoustic continuities between the fingers. We collect these signals using a novel array of sensors worn as an armband. When an intensity threshold was exceeded, the program recorded the timestamp as a potential start of a tap. Speech input is a logical choice for always- available input, but is limited in its precision in unpredictable acoustic environments, and suffers from privacy and scalability issues in shared environments. In particular, when placed on the upper arm above the elbow , we hoped to collect acoustic information from the fleshy bicep area in addition to the firmer area on the underside of the arm, with better acoustic coupling to the Humerus, the main bone that runs from shoulder to elbow.
This approach slinput feasible, but suffers from serious occlusion and accuracy limitations. In contrast, brain signals have been harnessed ksinput a direct input for use by paralyzed patients, but direct brain computer interfaces BCIs still lacks the bandwidth required for everyday computing tasks, and require levels of focus, training, and concentration that are incompatible with typical computer interaction.
There has been less work relating to the intersection of finger input and biological signals. In the paper linked below, we present our research on Skinput — a method that allows the body reseach be appropriated for finger input using a novel, non-invasive, wearable bio-acoustic sensor. We assess the capabilities, accuracy and limitations of our technique through a two-part, twenty-participant user study. Finally, our sensor design is relatively inexpensive and can be manufactured in a very small form factor e.
As such, we found them to be lacking in several significant ways. The audio stream was segmented into individual taps using an absolute exponential average of all ten channels.
For example, describes a technique that allows a small mobile device to turn tables on which it rests into a gestural finger input canvas.
Chris Harrison | Skinput
Inspection of the confusion matrices showed no systematic errors in the classification, with errors tending to be evenly distributed over the other digits. These include single-handed gestures, taps with different parts of the finger, and differentiating between materials and objects. Apart from the efforts of me, the success of this project depends largely on the encouragement and guidelines of many others.
This is not surprising, as this condition placed the sensors closer to the input targets than the other conditions. For example, we can readily flick each of our fingers, touch the tip of our nose, and clap our hands together without visual assistance.
For example, Scratch Input is technique that allows a small mobile device to turn tables on which it rests into a gestural finger input canvas. Remember me on this computer.
So in a few years researcj, with Skinput, computing is always available: Few external input devices can claim this accurate, eyes-free input characteristic and provide such a large interaction area. Adding more mass lowers the range of excitation to which a sensor responds; we weighted each element such that it aligned with particular frequencies that pilot studies showed to be useful in characterizing bio-acoustic input.
The decision to have two sensor packages was motivated by our focus on the arm for input. These are fed into gesearch trained SVM for classification.
Skinput: appropriating the body as an input surface
This is almost certainly related to the acoustic loss at the elbow joint and the additional 10cm of distance between the sensor and input targets. This is unsurprising given the morphology of the arm, with a high degree of bilateral symmetry along the long axis. It should be noted, however, that other, more sophisticated classification techniques and features could be employed. Bones are held together by ligaments, and joints often include additional biological structures such as fluid cavities.
This suggests there are only limited acoustic continuities between the fingers. However, papdr small size typically leads to limited interaction space e. Any interactive features bound to that event are fired. In our prototype system, we choose to focus on the arm although the technique could be applied elsewhere.
For example, determining whether, e. While bone conduction microphones might seem a suitable choice for Skinput, these devices are typically engineered for capturing human voice, and filter out energy below the range of human speech whose lowest frequency is around 85Hz.
At present, however, this approach typically requires expensive amplification systems and the application of conductive gel for effective signal acquisition, which would limit the acceptability of this approach for most users. This makes joints behave as acoustic filters. It describes a novel, wearable bio-acoustic sensing array that we built into an armband in order to detect and localize finger taps on the forearm and hand.
Subsequent feature selection established the all-pairs amplitude ratios and certain bands of the FFT to be the most predictive features. Each location thus provided slightly different acoustic coverage and reearch, helpful in disambiguating input location. Segmentation, as in other conditions, was essentially perfect.