A FAST FINGERTIP DETECTOR BASED ON THE CHORD-TO-POINT DISTANCE ACCUMULATION TECHNIQUE
A FAST FINGERTIP DETECTOR BASED ON THE CHORD-TO-POINT DISTANCE ACCUMULATION TECHNIQUE
- Author(s): W. Wang 1 and Y. Wang 1
- DOI: 10.1049/icp.2021.1416
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): W. Wang 1 and Y. Wang 1
-
-
View affiliations
-
Affiliations:
1:
School of Energy and Electrical Engineering, Hohai University , Nanjing , People's Republic of China
Source:
Jiangsu Annual Conference on Automation (JACA 2020),
2021
p.
16 – 20
-
Affiliations:
1:
School of Energy and Electrical Engineering, Hohai University , Nanjing , People's Republic of China
- Conference: Jiangsu Annual Conference on Automation (JACA 2020)
- DOI: 10.1049/icp.2021.1416
- ISBN: 978-1-83953-563-5
- Location: Zhenjiang, Jiangsu Province, China
- Conference date: 13-15 November 2020
- Format: PDF
In order to meet the needs of fingertip recognition and understanding in human-computer interaction system based on vision, real-time accurate positioning of fingertip is realized.In this paper, a fingertip detection method based on Fast-CPDA is proposed.Firstly, the image acquired by the image acquisition system is preprocessed, including median filtering, binarization based on skin color space, and morphological processing. The possible fingertip candidate points are obtained by Gaussian smoothing according to the different curvature characteristics of hand contour curve at different positions.On this basis, the chord to point distance accumulation algorithm combined with the boundary features of fingertip is used to realize the fast and accurate fingertip detection.Experimental results show that this method can detect fingertip position quickly and effectively, and has strong real-time and robustness in fingertip recognition.
Inspec keywords: image filtering; median filters; image colour analysis; Gaussian processes; edge detection; human computer interaction; object detection; computer vision
Subjects: User interfaces; Image recognition; Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics; Filtering methods in signal processing