A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition
Automatic recognition of hand postures is an important research topic with many applications, e.g., communication support for deaf people. In this paper, we present a novel four-stage, Mahalanobis-distance-based method for hand posture recognition using skeletal data. The proposed method is based on...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/22/12347 |
| _version_ | 1797460255813140480 |
|---|---|
| author | Dawid Warchoł Tomasz Kapuściński |
| author_facet | Dawid Warchoł Tomasz Kapuściński |
| author_sort | Dawid Warchoł |
| collection | DOAJ |
| description | Automatic recognition of hand postures is an important research topic with many applications, e.g., communication support for deaf people. In this paper, we present a novel four-stage, Mahalanobis-distance-based method for hand posture recognition using skeletal data. The proposed method is based on a two-stage classification algorithm with two additional stages related to joint preprocessing (normalization) and a rule-based system, specific to hand shapes that the algorithm is meant to classify. The method achieves superior effectiveness on two benchmark datasets, the first of which was created by us for the purpose of this work, while the second is a well-known and publicly available dataset. The method’s recognition rate measured by leave-one-subject-out cross-validation tests is 94.69% on the first dataset and 97.44% on the second. Experiments, including comparison with other state-of-the-art methods and ablation studies related to classification accuracy and time, confirm the effectiveness of our approach. |
| first_indexed | 2024-03-09T17:03:33Z |
| format | Article |
| id | doaj.art-715daf70f10c4be2bee6ced96fe6d86d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:03:33Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-715daf70f10c4be2bee6ced96fe6d86d2023-11-24T14:27:22ZengMDPI AGApplied Sciences2076-34172023-11-0113221234710.3390/app132212347A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture RecognitionDawid Warchoł0Tomasz Kapuściński1Department of Computer and Control Engineering, Faculty of Electrical and Computer Engineering, Rzeszów University of Technology, W. Pola 2, 35-959 Rzeszów, PolandDepartment of Computer and Control Engineering, Faculty of Electrical and Computer Engineering, Rzeszów University of Technology, W. Pola 2, 35-959 Rzeszów, PolandAutomatic recognition of hand postures is an important research topic with many applications, e.g., communication support for deaf people. In this paper, we present a novel four-stage, Mahalanobis-distance-based method for hand posture recognition using skeletal data. The proposed method is based on a two-stage classification algorithm with two additional stages related to joint preprocessing (normalization) and a rule-based system, specific to hand shapes that the algorithm is meant to classify. The method achieves superior effectiveness on two benchmark datasets, the first of which was created by us for the purpose of this work, while the second is a well-known and publicly available dataset. The method’s recognition rate measured by leave-one-subject-out cross-validation tests is 94.69% on the first dataset and 97.44% on the second. Experiments, including comparison with other state-of-the-art methods and ablation studies related to classification accuracy and time, confirm the effectiveness of our approach.https://www.mdpi.com/2076-3417/13/22/12347hand posture recognitionstatic gesture recognitionPolish finger alphabetAmerican finger alphabetmultistage classificationMahalanobis distance |
| spellingShingle | Dawid Warchoł Tomasz Kapuściński A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition Applied Sciences hand posture recognition static gesture recognition Polish finger alphabet American finger alphabet multistage classification Mahalanobis distance |
| title | A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition |
| title_full | A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition |
| title_fullStr | A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition |
| title_full_unstemmed | A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition |
| title_short | A Four-Stage Mahalanobis-Distance-Based Method for Hand Posture Recognition |
| title_sort | four stage mahalanobis distance based method for hand posture recognition |
| topic | hand posture recognition static gesture recognition Polish finger alphabet American finger alphabet multistage classification Mahalanobis distance |
| url | https://www.mdpi.com/2076-3417/13/22/12347 |
| work_keys_str_mv | AT dawidwarchoł afourstagemahalanobisdistancebasedmethodforhandposturerecognition AT tomaszkapuscinski afourstagemahalanobisdistancebasedmethodforhandposturerecognition AT dawidwarchoł fourstagemahalanobisdistancebasedmethodforhandposturerecognition AT tomaszkapuscinski fourstagemahalanobisdistancebasedmethodforhandposturerecognition |