Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network
Abstract Hand pose recognition has been one of the most fundamental tasks in computer vision and pattern recognition, and substantial effort has been devoted to this field. However, owing to lack of public large‐scale benchmark dataset, there is little literature to specially study pen‐holding hand...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-11-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12079 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832546658161786880 |
|---|---|
| author | Pingping Wu Lunke Fei Shuyi Li Shuping Zhao Xiaozhao Fang Shaohua Teng |
| author_facet | Pingping Wu Lunke Fei Shuyi Li Shuping Zhao Xiaozhao Fang Shaohua Teng |
| author_sort | Pingping Wu |
| collection | DOAJ |
| description | Abstract Hand pose recognition has been one of the most fundamental tasks in computer vision and pattern recognition, and substantial effort has been devoted to this field. However, owing to lack of public large‐scale benchmark dataset, there is little literature to specially study pen‐holding hand pose (PHHP) recognition. As an attempt to fill this gap, in this paper, a PHHP image dataset, consisting of 18,000 PHHP samples is established. To the best of the authors’ knowledge, this is the largest vision‐based PHHP dataset ever collected. Furthermore, the authors design a coarse‐to‐fine PHHP recognition network consisting of a coarse multi‐feature learning network and a fine pen‐grasping‐specific feature learning network, where the coarse learning network aims to extensively exploit the multiple discriminative features by sharing a hand‐shape‐based spatial attention information, and the fine learning network further learns the pen‐grasping‐specific features by embedding a couple of convolutional block attention modules into three convolution blocks models. Experimental results show that the authors’ proposed method can achieve a very competitive PHHP recognition performance when compared with the baseline recognition models. |
| format | Article |
| id | doaj-art-43ee96f244494410aa4a139a7a3dfc4e |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2022-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-43ee96f244494410aa4a139a7a3dfc4e2025-02-03T06:47:36ZengWileyIET Biometrics2047-49382047-49462022-11-0111658158710.1049/bme2.12079Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition networkPingping Wu0Lunke Fei1Shuyi Li2Shuping Zhao3Xiaozhao Fang4Shaohua Teng5School of Computer Science and Technology Guangdong University of Technology Guangzhou ChinaSchool of Computer Science and Technology Guangdong University of Technology Guangzhou ChinaDepartment of Computer and Information Science University of Macau Taipa Macau ChinaSchool of Computer Science and Technology Guangdong University of Technology Guangzhou ChinaSchool of Computer Science and Technology Guangdong University of Technology Guangzhou ChinaSchool of Computer Science and Technology Guangdong University of Technology Guangzhou ChinaAbstract Hand pose recognition has been one of the most fundamental tasks in computer vision and pattern recognition, and substantial effort has been devoted to this field. However, owing to lack of public large‐scale benchmark dataset, there is little literature to specially study pen‐holding hand pose (PHHP) recognition. As an attempt to fill this gap, in this paper, a PHHP image dataset, consisting of 18,000 PHHP samples is established. To the best of the authors’ knowledge, this is the largest vision‐based PHHP dataset ever collected. Furthermore, the authors design a coarse‐to‐fine PHHP recognition network consisting of a coarse multi‐feature learning network and a fine pen‐grasping‐specific feature learning network, where the coarse learning network aims to extensively exploit the multiple discriminative features by sharing a hand‐shape‐based spatial attention information, and the fine learning network further learns the pen‐grasping‐specific features by embedding a couple of convolutional block attention modules into three convolution blocks models. Experimental results show that the authors’ proposed method can achieve a very competitive PHHP recognition performance when compared with the baseline recognition models.https://doi.org/10.1049/bme2.12079deep learning networkhand pose recognitionjoint feature learningpen‐holding hand pose recognition |
| spellingShingle | Pingping Wu Lunke Fei Shuyi Li Shuping Zhao Xiaozhao Fang Shaohua Teng Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network IET Biometrics deep learning network hand pose recognition joint feature learning pen‐holding hand pose recognition |
| title | Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network |
| title_full | Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network |
| title_fullStr | Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network |
| title_full_unstemmed | Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network |
| title_short | Towards pen‐holding hand pose recognition: A new benchmark and a coarse‐to‐fine PHHP recognition network |
| title_sort | towards pen holding hand pose recognition a new benchmark and a coarse to fine phhp recognition network |
| topic | deep learning network hand pose recognition joint feature learning pen‐holding hand pose recognition |
| url | https://doi.org/10.1049/bme2.12079 |
| work_keys_str_mv | AT pingpingwu towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork AT lunkefei towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork AT shuyili towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork AT shupingzhao towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork AT xiaozhaofang towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork AT shaohuateng towardspenholdinghandposerecognitionanewbenchmarkandacoarsetofinephhprecognitionnetwork |