Natural hand gestures for human identification in a Human-Computer Interface

Romaszewski, Michał; Głomb, Przemysław; Gawron, Piotr

doi:10.1109/ipta.2014.7001997

Cited by 5 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Romaszewski et al used a list of 22 natural hand gesture. They first re-sampled and interpolated data, then applied LDA to discriminate the re-sampled segments with an accuracy of 92.8% [25]. However, in a live recognition system, this re-sampling and interpolation is not possible.…”

Section: Related Workmentioning

confidence: 99%

Designing a Sensor Glove Using Deep Learning

Chan

Veas

Simon

2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

When designing a smart glove for gesture recognition, the set of sensors available and their layout on the glove are crucial. However, once a computational model reaches acceptable recognition accuracy, it is often not clear which sensors are more important for the task. Nor whether some sensors can be strategically removed while retaining similar performance in order to save cost. Furthermore, when aiming for a personalized setup, there can be minor deviation in how gestures are performed by each participant, and so the importance of a sensor may vary between participants. In this paper, we use feature selection to explore whether a personalised glove can be produced, and whether the set of significant sensors persist between users. We present a deep learning algorithm which utilises a layer of weights to estimate the importance of each sensor in relation to each other. Besides estimating importance in relation to recognition accuracy, it is demonstrated how the importance estimates can be extended to take into account factors external to the computational model, such as costs. This allows for a cost effective elimination of sensors to reduce hardware redundancy whilst having a controlled impact on performance. We provide 2 methods: generic or specific. The generic method exploits the importance estimate from all participants to select a set of sensors for removal. Whereas the specific method estimates importance, and removes sensors based on individuals to provide a personalised setup. CCS CONCEPTS• Human-centered computing → Gestural input; • Computing methodologies → Neural networks; Feature selection; • Hardware → Sensor devices and platforms.

show abstract

Section: Related Workmentioning

confidence: 99%

Designing a Sensor Glove Using Deep Learning

Chan

Veas

Simon

2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…The mapping is natural, as it corresponds to movement of focus point within the sentence. Additionally, the interactions are easy to perform and considered in the research community as natural hand gestures [42,15,26] meaning that most users would be familiar with them. As for current word interaction, we map it to swipe up gesture as it shares the simplicity and popularity with the other selected gestures.…”

Section: Gesture Mappingmentioning

confidence: 99%

Investigating Interactions for Text Recognition using a Vibrotactile Wearable Display

Luzhnica

Veas

2018

23rd International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Vibrotactile skin-reading uses wearable vibrotactile displays to convey dynamically generated textual information. Such wearable displays have potential to be used in a broad range of applications. Nevertheless, the reading process is passive, and users have no control over the reading flow. To compensate for such drawback, this paper investigates what kind of interactions are necessary for vibrotactile skin reading and the modalities of such interactions. An interaction concept for skin reading was designed by taking into account the reading as a process. We performed a formative study with 22 participants to assess reading behaviour in word and sentence reading using a six-channel wearable vibrotactile display. Our study shows that word based interactions in sentence reading are more often used and preferred by users compared to character-based interactions and that users prefer gesturebased interaction for skin reading. Finally, we discuss how such wearable vibrotactile displays could be extended with sensors that would enable recognition of such gesture-based interaction. This paper contributes a set of guidelines for the design of wearable haptic displays for text communication.

show abstract

“…Literature provides several examples of MLT applied to human movement analysis; for instance, in 2014 Romaszewski et al applied Linear Discriminant Analysis (LDA), Support Vector Machine and k Nearest Neighbor algorithms to identify natural hand gestures [ 17 ]. In 2015, Li et al discriminated eight different movements of the upper limb exploiting the Random Forest (RF) algorithm for the analysis of optoelectronic data [ 18 ], whereas in 2020, Robertson et al applied the quadratic discriminant analysis to data acquired with a Kinect camera (© Microsoft Corporation, Redmond, WA, USA) to discriminate between healthy subjects and patients affected by Cerebellar Ataxia [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Intention Prediction and Human Health Condition Detection in Reaching Tasks with Machine Learning Techniques

Ragni

Archetti

Roby-Brami

et al. 2021

Sensors

View full text Add to dashboard Cite

Detecting human motion and predicting human intentions by analyzing body signals are challenging but fundamental steps for the implementation of applications presenting human–robot interaction in different contexts, such as robotic rehabilitation in clinical environments, or collaborative robots in industrial fields. Machine learning techniques (MLT) can face the limit of small data amounts, typical of this kind of applications. This paper studies the illustrative case of the reaching movement in 10 healthy subjects and 21 post-stroke patients, comparing the performance of linear discriminant analysis (LDA) and random forest (RF) in: (i) predicting the subject’s intention of moving towards a specific direction among a set of possible choices, (ii) detecting if the subject is moving according to a healthy or pathological pattern, and in the case of discriminating the damage location (left or right hemisphere). Data were captured with wearable electromagnetic sensors, and a sub-section of the acquired signals was required for the analyses. The possibility of detecting with which arm (left or right hand) the motion was performed, and the sensitivity of the MLT to variations in the length of the signal sub-section were also evaluated. LDA and RF prediction accuracies were compared: Accuracy improves when only healthy subjects or longer signals portions are considered up to 11% and at least 10%, respectively. RF reveals better estimation performance both as intention predictor (on average 59.91% versus the 62.19% of LDA), and health condition detector (over 90% in all the tests).

show abstract

Natural hand gestures for human identification in a Human-Computer Interface

Cited by 5 publications

References 26 publications

Designing a Sensor Glove Using Deep Learning

Designing a Sensor Glove Using Deep Learning

Investigating Interactions for Text Recognition using a Vibrotactile Wearable Display

Intention Prediction and Human Health Condition Detection in Reaching Tasks with Machine Learning Techniques

Contact Info

Product

Resources

About