Enhancing Input On and Above the Interactive Surface with Muscle Sensing

Hrvoje Benko, T. Scott Saponas, Dan Morris, and Desney Tan

Summarized & Presented by:Reem Alattas

Combining Muscle and Touch Sensing

• Touch-sensitive surfaces and EMG provide complementary streams of information.– Touch-sensitive surfaces provide precise location

and tracking information.– EMG can detect which muscle groups, and

consequently which fingers, are engaged in the current interaction.

Hardware and Setup

• Microsoft Surface• BioSemi Active Two EMG device– Samples eight sensor channels at 2048 Hz– 6 sensors and two ground electrodes around the

upper forearm of the dominant hand– 2 sensors on the forearm of the non-dominant

hand

Interpretation of Muscle Signals

• Level of pressure• Contact finger identification• “Pinch” and “Throw” gestures• “Flick” gesture

Hybrid EMG-Surface Interactions

• Pressure-sensitive painting• Finger-aware painting • Finger-dependent pick and throw • Undo flick

Exploratory System Evaluation

• Participants: 6 (3 females)• 90 minutes• $10 compensation

Goals

• Feasibility Validation• Reliability Assessment

Tasks• Task 1

– Copy an image from a given paper template using the pressure-sensitive painting technique

• Task 2– Copy an image from a given paper template using the finger-aware painting

technique• Task 3

– Make a series of vertical lines across the surface, changing color with each vertical line

• Task 4– Write the numbers from 1 to 10 on the surface, executing the “undo flick” gesture

after each even number, but not after odd numbers.• Task 5

– Presented with a pile of six images on a canvas, either copy or move each image to another canvas, depending on the image category.

Tasks

Results

Results• Task 1 mean accuracy = 93.9%

– All participants were able to effectively manipulate pressure to control brush darkness.

• Task 2:– All six participants completed the target drawing. – One had some difficulty reliably selecting the finger color.

• Task 3 mean accuracy = 90.9%• Task 4:

– Five out of six participants were able to reliably execute and control the “undo flick” gesture without any false positives.

• Task 5:– Three perfect executions

Conclusion

• The proposed approach enhances the existing tabletop paradigm and enables new interaction techniques not typically possible with standard interactive surfaces.

Questions