• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

使用神经形态传感器和人工神经网络识别美国手语字母。

American Sign Language Alphabet Recognition Using a Neuromorphic Sensor and an Artificial Neural Network.

机构信息

Advanced Studies and Research Center (CINVESTAV), National Polytechnic Institute (IPN), Zapopan 45019, Mexico.

CONACYT-Advanced Studies and Research Center (CINVESTAV), National Polytechnic Institute (IPN), Zapopan 45019, Mexico.

出版信息

Sensors (Basel). 2017 Sep 22;17(10):2176. doi: 10.3390/s17102176.

DOI:10.3390/s17102176
PMID:28937644
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC5677181/
Abstract

This paper reports the design and analysis of an American Sign Language (ASL) alphabet translation system implemented in hardware using a Field-Programmable Gate Array. The system process consists of three stages, the first being the communication with the neuromorphic camera (also called Dynamic Vision Sensor, DVS) sensor using the Universal Serial Bus protocol. The feature extraction of the events generated by the DVS is the second part of the process, consisting of a presentation of the digital image processing algorithms developed in software, which aim to reduce redundant information and prepare the data for the third stage. The last stage of the system process is the classification of the ASL alphabet, achieved with a single artificial neural network implemented in digital hardware for higher speed. The overall result is the development of a classification system using the ASL signs contour, fully implemented in a reconfigurable device. The experimental results consist of a comparative analysis of the recognition rate among the alphabet signs using the neuromorphic camera in order to prove the proper operation of the digital image processing algorithms. In the experiments performed with 720 samples of 24 signs, a recognition accuracy of 79.58% was obtained.

摘要

本文报告了一个使用现场可编程门阵列（FPGA）硬件实现的美国手语（ASL）字母翻译系统的设计和分析。该系统的处理过程分为三个阶段，第一阶段是使用通用串行总线（USB）协议与神经形态相机（也称为动态视觉传感器，DVS）传感器进行通信。DVS 生成的事件的特征提取是该过程的第二部分，包括开发的软件数字图像处理算法的介绍，这些算法旨在减少冗余信息并为第三阶段准备数据。系统处理的最后一个阶段是 ASL 字母的分类，通过在数字硬件中实现单个人工神经网络来实现更高的速度。整体结果是开发了一种使用 ASL 符号轮廓的分类系统，完全在可重构设备中实现。实验结果包括使用神经形态相机对字母符号的识别率进行比较分析，以证明数字图像处理算法的正常运行。在对 24 个符号的 720 个样本进行的实验中，获得了 79.58%的识别准确率。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/3c24d4562d62/sensors-17-02176-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/42178fcff19c/sensors-17-02176-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/909401bdd2b5/sensors-17-02176-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/11b96e604c1f/sensors-17-02176-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/ae502028abc8/sensors-17-02176-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/d267940547c0/sensors-17-02176-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/93c2226a8eb4/sensors-17-02176-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/baaff73c7404/sensors-17-02176-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/455f54a3a096/sensors-17-02176-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/c9194d708333/sensors-17-02176-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9f9b02be15a6/sensors-17-02176-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/913ece426a63/sensors-17-02176-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/fc6da88e1f90/sensors-17-02176-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9f7ef0685d49/sensors-17-02176-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/a0cf2c71ced3/sensors-17-02176-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9c882f92f258/sensors-17-02176-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/834a7b387e2e/sensors-17-02176-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/8478aaacf947/sensors-17-02176-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/600c8524bfa1/sensors-17-02176-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/617d30204942/sensors-17-02176-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/a319dc5cc1d8/sensors-17-02176-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/da39f979e7ba/sensors-17-02176-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/3c24d4562d62/sensors-17-02176-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/42178fcff19c/sensors-17-02176-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/909401bdd2b5/sensors-17-02176-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/11b96e604c1f/sensors-17-02176-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/ae502028abc8/sensors-17-02176-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/d267940547c0/sensors-17-02176-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/93c2226a8eb4/sensors-17-02176-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/baaff73c7404/sensors-17-02176-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/455f54a3a096/sensors-17-02176-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/c9194d708333/sensors-17-02176-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9f9b02be15a6/sensors-17-02176-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/913ece426a63/sensors-17-02176-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/fc6da88e1f90/sensors-17-02176-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9f7ef0685d49/sensors-17-02176-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/a0cf2c71ced3/sensors-17-02176-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/9c882f92f258/sensors-17-02176-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/834a7b387e2e/sensors-17-02176-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/8478aaacf947/sensors-17-02176-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/600c8524bfa1/sensors-17-02176-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/617d30204942/sensors-17-02176-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/a319dc5cc1d8/sensors-17-02176-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/da39f979e7ba/sensors-17-02176-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/56fb/5677181/3c24d4562d62/sensors-17-02176-g022.jpg

相似文献

1
American Sign Language Alphabet Recognition Using a Neuromorphic Sensor and an Artificial Neural Network.使用神经形态传感器和人工神经网络识别美国手语字母。
Sensors (Basel). 2017 Sep 22;17(10):2176. doi: 10.3390/s17102176.
2
American Sign Language Alphabet Recognition by Extracting Feature from Hand Pose Estimation.从手姿态估计中提取特征实现美国手语字母识别。
Sensors (Basel). 2021 Aug 31;21(17):5856. doi: 10.3390/s21175856.
3
Image processing system for interpreting motion in American Sign Language.用于解读美式手语动作的图像处理系统。
J Biomed Eng. 1992 Sep;14(5):419-25. doi: 10.1016/0141-5425(92)90088-3.
4
British Sign Language Recognition via Late Fusion of Computer Vision and Leap Motion with Transfer Learning to American Sign Language.基于计算机视觉和 Leap Motion 的迁移学习的英国手语识别与美国手语的融合
Sensors (Basel). 2020 Sep 9;20(18):5151. doi: 10.3390/s20185151.
5
Hand-Gesture Recognition Based on EMG and Event-Based Camera Sensor Fusion: A Benchmark in Neuromorphic Computing.基于肌电图和基于事件的相机传感器融合的手势识别：神经形态计算中的一个基准
Front Neurosci. 2020 Aug 5;14:637. doi: 10.3389/fnins.2020.00637. eCollection 2020.
6
Neural network feature detector for real-time video signal processing.用于实时视频信号处理的神经网络特征检测器。
Int J Neural Syst. 1993 Dec;4(4):337-49. doi: 10.1142/s0129065793000286.
7
Towards real-time and rotation-invariant American Sign Language alphabet recognition using a range camera.使用距离摄像机实现实时和旋转不变的美国手语字母识别。
Sensors (Basel). 2012 Oct 29;12(11):14416-41. doi: 10.3390/s121114416.
8
Hypertuned Deep Convolutional Neural Network for Sign Language Recognition.超调深度卷积神经网络的手语识别。
Comput Intell Neurosci. 2022 Apr 30;2022:1450822. doi: 10.1155/2022/1450822. eCollection 2022.
9
Sign language recognition and translation: a multidisciplined approach from the field of artificial intelligence.手语识别与翻译：人工智能领域的多学科方法。
J Deaf Stud Deaf Educ. 2006 Winter;11(1):94-101. doi: 10.1093/deafed/enj003. Epub 2005 Sep 28.
10
American Sign Language Recognition Using Leap Motion Controller with Machine Learning Approach.使用 Leap Motion 控制器和机器学习方法进行美国手语识别。
Sensors (Basel). 2018 Oct 19;18(10):3554. doi: 10.3390/s18103554.

引用本文的文献

1
Sign language recognition using the fusion of image and hand landmarks through multi-headed convolutional neural network.基于多头卷积神经网络的融合图像和手地标进行手语识别。
Sci Rep. 2023 Oct 9;13(1):16975. doi: 10.1038/s41598-023-43852-x.
2
A Sign Language Recognition System Applied to Deaf-Mute Medical Consultation.手语识别系统在聋哑人医疗咨询中的应用。
Sensors (Basel). 2022 Nov 24;22(23):9107. doi: 10.3390/s22239107.
3
Full-Fiber Auxetic-Interlaced Yarn Sensor for Sign-Language Translation Glove Assisted by Artificial Neural Network.

本文引用的文献

1
Real-time gesture interface based on event-driven processing from stereo silicon retinas.基于立体硅视网膜事件驱动处理的实时手势界面。
IEEE Trans Neural Netw Learn Syst. 2014 Dec;25(12):2250-63. doi: 10.1109/TNNLS.2014.2308551.
2
Towards real-time and rotation-invariant American Sign Language alphabet recognition using a range camera.使用距离摄像机实现实时和旋转不变的美国手语字母识别。
Sensors (Basel). 2012 Oct 29;12(11):14416-41. doi: 10.3390/s121114416.
用于手语翻译手套的全纤维负泊松比交织纱线传感器，由人工神经网络辅助
Nanomicro Lett. 2022 Jul 1;14(1):139. doi: 10.1007/s40820-022-00887-5.
4
Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand Relationship Patterns.基于反手接近法的美国手语单词识别，使用时空身体部位和手部关系模式。
Sensors (Basel). 2022 Jun 16;22(12):4554. doi: 10.3390/s22124554.
5
American Sign Language Alphabet Recognition by Extracting Feature from Hand Pose Estimation.从手姿态估计中提取特征实现美国手语字母识别。
Sensors (Basel). 2021 Aug 31;21(17):5856. doi: 10.3390/s21175856.
6
Event-Based Gesture Recognition With Dynamic Background Suppression Using Smartphone Computational Capabilities.利用智能手机计算能力进行动态背景抑制的基于事件的手势识别
Front Neurosci. 2020 Apr 9;14:275. doi: 10.3389/fnins.2020.00275. eCollection 2020.