Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition
Hand Gesture Recognition (HGR) plays a crucial role in user-friendly interactions between humans and computers. In recent years, using the Convolutional Neural Network (CNN) has improved the accuracy of image processing problems. Inspired by the high recognition rate of CNN and its efficiency, we pr...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10332190/ |
| _version_ | 1797401029212372992 |
|---|---|
| author | Farzaneh Jafari Anup Basu |
| author_facet | Farzaneh Jafari Anup Basu |
| author_sort | Farzaneh Jafari |
| collection | DOAJ |
| description | Hand Gesture Recognition (HGR) plays a crucial role in user-friendly interactions between humans and computers. In recent years, using the Convolutional Neural Network (CNN) has improved the accuracy of image processing problems. Inspired by the high recognition rate of CNN and its efficiency, we propose a model for hand gesture recognition based on CNN and evaluate the results using images with plain and complex backgrounds. Recognizing different hand signs by Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling (2DPSTPP) features with deep learning methods reduces the size of the map, minimizes training complexity, and by paying attention to more details, improves detection performance. The effectiveness of the proposed method is evaluated using regular cross-validation tests on six datasets, namely American Sign Language (ASL), the NUS hand posture dataset I, the NUS hand posture dataset II, the digits dataset, the hand gesture dataset, and the leap gesture recognition dataset. |
| first_indexed | 2024-03-09T02:03:58Z |
| format | Article |
| id | doaj.art-9d5dad71a11b46cfad06007275b3feed |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-09T02:03:58Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9d5dad71a11b46cfad06007275b3feed2023-12-08T00:06:59ZengIEEEIEEE Access2169-35362023-01-011113375513376610.1109/ACCESS.2023.333659110332190Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture RecognitionFarzaneh Jafari0https://orcid.org/0009-0007-1901-2860Anup Basu1https://orcid.org/0000-0002-7695-4148Department of Computing Science, University of Alberta, Edmonton, CanadaDepartment of Computing Science, University of Alberta, Edmonton, CanadaHand Gesture Recognition (HGR) plays a crucial role in user-friendly interactions between humans and computers. In recent years, using the Convolutional Neural Network (CNN) has improved the accuracy of image processing problems. Inspired by the high recognition rate of CNN and its efficiency, we propose a model for hand gesture recognition based on CNN and evaluate the results using images with plain and complex backgrounds. Recognizing different hand signs by Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling (2DPSTPP) features with deep learning methods reduces the size of the map, minimizes training complexity, and by paying attention to more details, improves detection performance. The effectiveness of the proposed method is evaluated using regular cross-validation tests on six datasets, namely American Sign Language (ASL), the NUS hand posture dataset I, the NUS hand posture dataset II, the digits dataset, the hand gesture dataset, and the leap gesture recognition dataset.https://ieeexplore.ieee.org/document/10332190/ASL datasetconvolutional neural network (CNN)hand gesture detectionhand gesture datasetNUS hand posture dataset INUS hand posture dataset II |
| spellingShingle | Farzaneh Jafari Anup Basu Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition IEEE Access ASL dataset convolutional neural network (CNN) hand gesture detection hand gesture dataset NUS hand posture dataset I NUS hand posture dataset II |
| title | Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition |
| title_full | Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition |
| title_fullStr | Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition |
| title_full_unstemmed | Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition |
| title_short | Two-Dimensional Parallel Spatio-Temporal Pyramid Pooling for Hand Gesture Recognition |
| title_sort | two dimensional parallel spatio temporal pyramid pooling for hand gesture recognition |
| topic | ASL dataset convolutional neural network (CNN) hand gesture detection hand gesture dataset NUS hand posture dataset I NUS hand posture dataset II |
| url | https://ieeexplore.ieee.org/document/10332190/ |
| work_keys_str_mv | AT farzanehjafari twodimensionalparallelspatiotemporalpyramidpoolingforhandgesturerecognition AT anupbasu twodimensionalparallelspatiotemporalpyramidpoolingforhandgesturerecognition |