Gesture recognition using DTW &amp;amp; piecewise DTW

Jambhale, Sandeep S.; Khaparde, Arti

doi:10.1109/ecs.2014.6892646

Cited by 20 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic Time Warping: This technique shares similarities with speech recognition in that the process is a similarity measure of the input signal to that of a sample in the database [7].…”

Section: Image Recognition Techniquesmentioning

confidence: 99%

“…Static Gestures are observed in an instance of a period of time, and Dynamic Gestures are observed over a period of time [7]. However, this is a simplistic approach that observes directed movement.…”

Section: Gesture Classificationsmentioning

confidence: 99%

“…Gestures are usually compared to databases for successful recognition. A sub-set of shapes that is most designed for are sign-language [3] [9] [7]. Dynamic Gestures use motion tracking to compare to a predefined database entry, however, some track the simple transition of one gesture to another [11].…”

Section: Gesture Classificationsmentioning

confidence: 99%

“…The process proceeds as follows: image is identified as valid command by temporal definition or by state definition, a specific feature is extracted. The extracted feature is compared to database of predefined which will then decide what interpretation will fit the data most appropriately [3] [9] [7]. Some processing techniques commonly used for this type of recognition: K-mean [3], Markov Models [9], and Principle components analysis [7].…”

Section: Gesture Classificationsmentioning

confidence: 99%

See 3 more Smart Citations

The classification of gesture interactions and the study of their ergonomic effect on hands

Chau¹

2021

Preprint

View full text Add to dashboard Cite

In order to investigate gestural behavior during human-computer interactions, an investigation into the designs of current interaction methods is conducted. This information is then compared to current emerging databases to observe if the gesture designs follow guidelines discovered in the above investigation. The comparison will also observe common trends in the currently developed gesture databases such as similar gesture for specific commands. In order to investigate gestural behavior during interactions with computer interfaces, an experiment has been devised to observe and record gestures in use for gesture databases through the use of a hardware sensor device. It was discovered that factors such as opposing adjacent fingers and gestures that simulated object manipulation are factors in user comfort. The results of this study will create guidelines for creating new gestures for hand gesture interfaces.

show abstract

“…Dynamic Time Warping: This technique shares similarities with speech recognition in that the process is a similarity measure of the input signal to that of a sample in the database [7].…”

Section: Image Recognition Techniquesmentioning

confidence: 99%

Section: Gesture Classificationsmentioning

confidence: 99%

Section: Gesture Classificationsmentioning

confidence: 99%

Section: Gesture Classificationsmentioning

confidence: 99%

See 2 more Smart Citations

The classification of gesture interactions and the study of their ergonomic effect on hands

Chau¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Refs. [17,18] utilized DTW distance based matching methods for electrical appliance identification and gesture recognition. Hausdorff distance is used in [19] in order to cluster the spatio-temporal trajectory vectors.…”

Section: Profile Extraction With Non-euclidean Distancementioning

confidence: 99%

Load Profile Extraction by Mean-Shift Clustering with Sample Pearson Correlation Coefficient Distance

et al. 2018

View full text Add to dashboard Cite

In this paper, a clustering method with proposed distance measurement to extract base load profiles from arbitrary data sets is studied. Recently, smart energy load metering devices are broadly deployed, and an immense volume of data is now collected. However, as this large amount of data has been explosively generated over such a short period of time, the collected data is hardly organized to be employed for study, applications, services, and systems. This paper provides a foundation method to extract base load profiles that can be utilized by power engineers, energy system operators, and researchers for deeper analysis and more advanced technologies. The base load profiles allow them to understand the patterns residing in the load data to discover the greater value. Up to this day, experts with domain knowledge often have done the base load profile realization manually. However, the volume of the data is growing too fast to handle it with the conventional approach. Accordingly, an automated yet precise method to recognize and extract the base power load profiles is studied in this paper. For base load profile extraction, this paper proposes Sample Pearson Correlation Coefficient (SPCC) distance measurement and applies it to Mean-Shift algorithm based nonparametric mode-seeking clustering. The superiority of SPCC distance over traditional Euclidean distance is validated by mathematical and numerical analysis.

show abstract

Static Hand Gesture Recognition for Human Robot Interaction

Uwineza

et al. 2019

Intelligent Robotics and Applications

View full text Add to dashboard Cite

Gesture recognition using DTW & piecewise DTW

Cited by 20 publications

References 9 publications

The classification of gesture interactions and the study of their ergonomic effect on hands

The classification of gesture interactions and the study of their ergonomic effect on hands

Load Profile Extraction by Mean-Shift Clustering with Sample Pearson Correlation Coefficient Distance

Static Hand Gesture Recognition for Human Robot Interaction

Contact Info

Product

Resources

About