Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds
Biometrics has become an important research issue in recent years, and the use of deep learning neural networks has made it possible to develop more reliable and efficient recognition systems. Palms have been identified as one of the most promising candidates among various biometrics due to their un...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/7/381 |
| _version_ | 1797588888325193728 |
|---|---|
| author | Yu-Ming Zhang Chia-Yuan Cheng Chih-Lung Lin Chun-Chieh Lee Kuo-Chin Fan |
| author_facet | Yu-Ming Zhang Chia-Yuan Cheng Chih-Lung Lin Chun-Chieh Lee Kuo-Chin Fan |
| author_sort | Yu-Ming Zhang |
| collection | DOAJ |
| description | Biometrics has become an important research issue in recent years, and the use of deep learning neural networks has made it possible to develop more reliable and efficient recognition systems. Palms have been identified as one of the most promising candidates among various biometrics due to their unique features and easy accessibility. However, traditional palm recognition methods involve 3D point clouds, which can be complex and difficult to work with. To mitigate this challenge, this paper proposes two methods which are Multi-View Projection (MVP) and Light Inverted Residual Block (LIRB).The MVP simulates different angles that observers use to observe palms in reality. It transforms 3D point clouds into multiple 2D images and effectively reduces the loss of mapping 3D data to 2D data. Therefore, the MVP can greatly reduce the complexity of the system. In experiments, MVP demonstrated remarkable performance on various famous models, such as VGG or MobileNetv2, with a particular improvement in the performance of smaller models. To further improve the performance of small models, this paper applies LIRB to build a lightweight 2D CNN called Tiny-MobileNet (TMBNet).The TMBNet has only a few convolutional layers but outperforms the 3D baselines PointNet and PointNet++ in FLOPs and accuracy. The experimental results show that the proposed method can effectively mitigate the challenges of recognizing palms through 3D point clouds of palms. The proposed method not only reduces the complexity of the system but also extends the use of lightweight CNN. These findings have significant implications for developing biometrics and could lead to improvements in various fields, such as access control and security control. |
| first_indexed | 2024-03-11T00:58:25Z |
| format | Article |
| id | doaj.art-23de363f18544bf39d5bea1899f0ec42 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T00:58:25Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-23de363f18544bf39d5bea1899f0ec422023-11-18T19:46:50ZengMDPI AGInformation2078-24892023-07-0114738110.3390/info14070381Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point CloudsYu-Ming Zhang0Chia-Yuan Cheng1Chih-Lung Lin2Chun-Chieh Lee3Kuo-Chin Fan4Department of Computer Science and Information Engineering, National Central University, Taoyuan 320, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan 320, TaiwanDepartment of Computer Science and Information Engineering, Hwa Hsia University of Technology, New Taipei 173, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan 320, TaiwanDepartment of Computer Science and Information Engineering, National Central University, Taoyuan 320, TaiwanBiometrics has become an important research issue in recent years, and the use of deep learning neural networks has made it possible to develop more reliable and efficient recognition systems. Palms have been identified as one of the most promising candidates among various biometrics due to their unique features and easy accessibility. However, traditional palm recognition methods involve 3D point clouds, which can be complex and difficult to work with. To mitigate this challenge, this paper proposes two methods which are Multi-View Projection (MVP) and Light Inverted Residual Block (LIRB).The MVP simulates different angles that observers use to observe palms in reality. It transforms 3D point clouds into multiple 2D images and effectively reduces the loss of mapping 3D data to 2D data. Therefore, the MVP can greatly reduce the complexity of the system. In experiments, MVP demonstrated remarkable performance on various famous models, such as VGG or MobileNetv2, with a particular improvement in the performance of smaller models. To further improve the performance of small models, this paper applies LIRB to build a lightweight 2D CNN called Tiny-MobileNet (TMBNet).The TMBNet has only a few convolutional layers but outperforms the 3D baselines PointNet and PointNet++ in FLOPs and accuracy. The experimental results show that the proposed method can effectively mitigate the challenges of recognizing palms through 3D point clouds of palms. The proposed method not only reduces the complexity of the system but also extends the use of lightweight CNN. These findings have significant implications for developing biometrics and could lead to improvements in various fields, such as access control and security control.https://www.mdpi.com/2078-2489/14/7/381palms recognitionmulti-view projectionlightweight convolutional neural network |
| spellingShingle | Yu-Ming Zhang Chia-Yuan Cheng Chih-Lung Lin Chun-Chieh Lee Kuo-Chin Fan Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds Information palms recognition multi-view projection lightweight convolutional neural network |
| title | Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds |
| title_full | Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds |
| title_fullStr | Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds |
| title_full_unstemmed | Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds |
| title_short | Develop a Lightweight Convolutional Neural Network to Recognize Palms Using 3D Point Clouds |
| title_sort | develop a lightweight convolutional neural network to recognize palms using 3d point clouds |
| topic | palms recognition multi-view projection lightweight convolutional neural network |
| url | https://www.mdpi.com/2078-2489/14/7/381 |
| work_keys_str_mv | AT yumingzhang developalightweightconvolutionalneuralnetworktorecognizepalmsusing3dpointclouds AT chiayuancheng developalightweightconvolutionalneuralnetworktorecognizepalmsusing3dpointclouds AT chihlunglin developalightweightconvolutionalneuralnetworktorecognizepalmsusing3dpointclouds AT chunchiehlee developalightweightconvolutionalneuralnetworktorecognizepalmsusing3dpointclouds AT kuochinfan developalightweightconvolutionalneuralnetworktorecognizepalmsusing3dpointclouds |