The design of hand gestures for human–computer interaction: Lessons from sign language interpreters

Rempel, David; Camilleri, Matt; Lee, David L.

doi:10.1016/j.ijhcs.2014.05.003

Cited by 64 publications

(43 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characteristics of high discomfort gestures observed in this study (i.e., elevated/extended arms, static posture holding and wrist flexion/extension) have been recognized as risk factors of discomfort, pain and work-related musculoskeletal disorders in many industrial ergonomics studies [79,81–86]. [31] also reported similar findings on the postural similarities between uncomfortable hand/arm gestures and stressful industrial manual tasks.…”

Section: Discussionsupporting

confidence: 77%

Evaluating the utility of two gestural discomfort evaluation methods

2017

View full text Add to dashboard Cite

Evaluating physical discomfort of designed gestures is important for creating safe and usable gesture-based interaction systems; yet, gestural discomfort evaluation has not been extensively studied in HCI, and few evaluation methods seem currently available whose utility has been experimentally confirmed. To address this, this study empirically demonstrated the utility of the subjective rating method after a small number of gesture repetitions (a maximum of four repetitions) in evaluating designed gestures in terms of physical discomfort resulting from prolonged, repetitive gesture use. The subjective rating method has been widely used in previous gesture studies but without empirical evidence on its utility. This study also proposed a gesture discomfort evaluation method based on an existing ergonomics posture evaluation tool (Rapid Upper Limb Assessment) and demonstrated its utility in evaluating designed gestures in terms of physical discomfort resulting from prolonged, repetitive gesture use. Rapid Upper Limb Assessment is an ergonomics postural analysis tool that quantifies the work-related musculoskeletal disorders risks for manual tasks, and has been hypothesized to be capable of correctly determining discomfort resulting from prolonged, repetitive gesture use. The two methods were evaluated through comparisons against a baseline method involving discomfort rating after actual prolonged, repetitive gesture use. Correlation analyses indicated that both methods were in good agreement with the baseline. The methods proposed in this study seem useful for predicting discomfort resulting from prolonged, repetitive gesture use, and are expected to help interaction designers create safe and usable gesture-based interaction systems.

show abstract

Section: Discussionsupporting

confidence: 77%

Evaluating the utility of two gestural discomfort evaluation methods

2017

View full text Add to dashboard Cite

show abstract

“…From an ergonomic point of view, signi cant RoMs and proximity with joint limits are risk factors for onset of musculoskeletal disorders. For example, a variation of 30° from the elbow neutral position (Jane Cote Gil Coury et al 1998) or a exion/extension of the wrist over 15° (Faessen, Stee, and Rozendal 1989) were considered as binding positions or signi cant uncomfortable posture (Rempel, Camilleri, and Lee 2015). So, it appears that large displacements of virtual objects on the screen the display size on kinematics parameters such movement time (Accot and Zhai 2001;Lai and Wu 2014;Oehl, Sutter, and Zie e 2007): an increase in size conducted to an increase in the performance and a decrease in movement time.…”

Section: Discussionmentioning

confidence: 99%

Biomechanical analysis of upper limb during the use of touch screen: motion strategies identification

et al. 2016

View full text Add to dashboard Cite

Nowadays touch technology is growing and developers try to make it ever more intuitive and easier to use. This present work focused on the upper limb joint coordination during the achievement of puzzles on touch screen. A 5-inch and 10-inch devices were used to perform 9 and 16 pieces puzzles dragged with digits. The conclusions showed an increase in joint solicitation with the number of piece and the touch screen size. Moreover, three interactions strategies proved to be an evidence: the 'wrist strategy' preferentially implying wrist flexion/extension, the 'elbow strategy' preferentially implying the elbow flexion/extension and the 'neutral strategy' mobilising equally the two joints. From an ergonomic point of view, the data about how the upper limb segments are mobilised while interacting with the screen could be relevant to increase the adaptability of the devices to the user, including users with motor impairments. Practitioner Summary: Information about the biomechanical organisation of movement during interaction with touch devices appears relevant in order to develop applications adapted to the motor capacities of users. From the analysis of joint angles when performing several times a puzzle with healthy subjects, three motor strategies were highlighted.

show abstract

“…Kinematic hand model [7,31] tries to emulate the DoF of the human hand through fingers, joints, and their relative distances and angles primarily for robotic hands [10,33]. The vision based kinematic posture recognition approaches which are mostly contour-based adopt mechanisms like palm comprising of connected spheres [30], oriented radial distribution [40], Semi-supervised Transductive Regression Forest [41], and curve fitting [45] to implement DoFs.…”

Section: Literature Reviewmentioning

confidence: 99%

Real-time recognition of medial structures within hand postures through Eigen-space and geometric skeletal shape features

Kane

Khanna

2016

Multimed Tools Appl

View full text Add to dashboard Cite

Skeletons provide landmark points that preserve implicit strokes or medial structure within a shape for compact representation. Though, hand posture shapes are usually recognized by region or contour representations, some applications may only be interested in the recognition of medial structures within the postures rather than their exact outlines and regions. Proposed work identifies several unique medial structures formed by a set of both one and two-handed postures and demonstrates their pure skeletal recognition in real-time. Existing skeleton-based recognition schemes apply the complex segmental processing on underlying skeleton and rely on contour information which is not suitable for fast recognition of medial structures. Presented work applies intuitive Eigen-space based Principal Components of Symbolic Structure (PCSS) and geometric Equi-Polar Signature (EPS) features to accomplish the recognition task. Both PCV and EPS process the skeleton globally without sections without associating contour information. Recognition accuracy up to 94% is obtained on a 22 posture dataset comprising of 10,560 depth frames with 480 samples for each posture. Depth sensor based acquisition is employed to meet the real-time requirements.

show abstract

The design of hand gestures for human–computer interaction: Lessons from sign language interpreters

Cited by 64 publications

References 28 publications

Evaluating the utility of two gestural discomfort evaluation methods

Evaluating the utility of two gestural discomfort evaluation methods

Biomechanical analysis of upper limb during the use of touch screen: motion strategies identification

Real-time recognition of medial structures within hand postures through Eigen-space and geometric skeletal shape features

Contact Info

Product

Resources

About