Confusion matrix for letter gestures [30].
<div><p>Gesture interaction applications have garnered significant attention from researchers in the field of human-computer interaction due to their inherent convenience and intuitiveness. Addressing the challenge posed by the insufficient feature extraction capability of existing netwo...
Saved in:
| Main Author: | |
|---|---|
| Published: |
2025
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1852022599451672576 |
|---|---|
| author | Peixin Niu (12330204) |
| author_facet | Peixin Niu (12330204) |
| author_role | author |
| dc.creator.none.fl_str_mv | Peixin Niu (12330204) |
| dc.date.none.fl_str_mv | 2025-02-19T18:24:25Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0311941.g014 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Confusion_matrix_for_letter_gestures_30_/28445922 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Molecular Biology Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified scale convolutional module publicly available datasets network &# 8217 lightweight network models innovative design incorporates garnered significant attention feature extraction capabilities extract underlying features exponential linear unit existing network models enhanced mobilenet network empirical findings demonstrate creative senz3d datasets convolutional neural network computer interaction due activation function enhances paper attains 92 gesture recognition human paper introduces thereby augmenting proposed model maintaining real inherent convenience impressive 98 challenge posed approach surpasses |
| dc.title.none.fl_str_mv | Confusion matrix for letter gestures [30]. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Gesture interaction applications have garnered significant attention from researchers in the field of human-computer interaction due to their inherent convenience and intuitiveness. Addressing the challenge posed by the insufficient feature extraction capability of existing network models, which hampers gesture recognition accuracy and increases model inference time, this paper introduces a novel gesture recognition algorithm based on an enhanced MobileNet network. This innovative design incorporates a multi-scale convolutional module to extract underlying features, thereby augmenting the network’s feature extraction capabilities. Moreover, the utilization of an exponential linear unit (ELU) activation function enhances the capture of comprehensive negative feature information. Empirical findings demonstrate that our approach surpasses the accuracy achieved by most lightweight network models on publicly available datasets, all while maintaining real-time gesture interaction capabilities. The accuracy of the proposed model in this paper attains 92.55% and 88.41% on the NUS-II and Creative Senz3D datasets, respectively, and achieves an impressive 98.26% on the ASL-M dataset.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_e4cfccc8c1ae7c3d5d9db62dbcaca4df |
| identifier_str_mv | 10.1371/journal.pone.0311941.g014 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/28445922 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Confusion matrix for letter gestures [30].Peixin Niu (12330204)Molecular BiologyBiotechnologyScience PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedscale convolutional modulepublicly available datasetsnetwork &# 8217lightweight network modelsinnovative design incorporatesgarnered significant attentionfeature extraction capabilitiesextract underlying featuresexponential linear unitexisting network modelsenhanced mobilenet networkempirical findings demonstratecreative senz3d datasetsconvolutional neural networkcomputer interaction dueactivation function enhancespaper attains 92gesture recognition humanpaper introducesthereby augmentingproposed modelmaintaining realinherent convenienceimpressive 98challenge posedapproach surpasses<div><p>Gesture interaction applications have garnered significant attention from researchers in the field of human-computer interaction due to their inherent convenience and intuitiveness. Addressing the challenge posed by the insufficient feature extraction capability of existing network models, which hampers gesture recognition accuracy and increases model inference time, this paper introduces a novel gesture recognition algorithm based on an enhanced MobileNet network. This innovative design incorporates a multi-scale convolutional module to extract underlying features, thereby augmenting the network’s feature extraction capabilities. Moreover, the utilization of an exponential linear unit (ELU) activation function enhances the capture of comprehensive negative feature information. Empirical findings demonstrate that our approach surpasses the accuracy achieved by most lightweight network models on publicly available datasets, all while maintaining real-time gesture interaction capabilities. The accuracy of the proposed model in this paper attains 92.55% and 88.41% on the NUS-II and Creative Senz3D datasets, respectively, and achieves an impressive 98.26% on the ASL-M dataset.</p></div>2025-02-19T18:24:25ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0311941.g014https://figshare.com/articles/figure/Confusion_matrix_for_letter_gestures_30_/28445922CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/284459222025-02-19T18:24:25Z |
| spellingShingle | Confusion matrix for letter gestures [30]. Peixin Niu (12330204) Molecular Biology Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified scale convolutional module publicly available datasets network &# 8217 lightweight network models innovative design incorporates garnered significant attention feature extraction capabilities extract underlying features exponential linear unit existing network models enhanced mobilenet network empirical findings demonstrate creative senz3d datasets convolutional neural network computer interaction due activation function enhances paper attains 92 gesture recognition human paper introduces thereby augmenting proposed model maintaining real inherent convenience impressive 98 challenge posed approach surpasses |
| status_str | publishedVersion |
| title | Confusion matrix for letter gestures [30]. |
| title_full | Confusion matrix for letter gestures [30]. |
| title_fullStr | Confusion matrix for letter gestures [30]. |
| title_full_unstemmed | Confusion matrix for letter gestures [30]. |
| title_short | Confusion matrix for letter gestures [30]. |
| title_sort | Confusion matrix for letter gestures [30]. |
| topic | Molecular Biology Biotechnology Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified scale convolutional module publicly available datasets network &# 8217 lightweight network models innovative design incorporates garnered significant attention feature extraction capabilities extract underlying features exponential linear unit existing network models enhanced mobilenet network empirical findings demonstrate creative senz3d datasets convolutional neural network computer interaction due activation function enhances paper attains 92 gesture recognition human paper introduces thereby augmenting proposed model maintaining real inherent convenience impressive 98 challenge posed approach surpasses |