Wrist detection based on a minimum bounding box and geometric features
Wrist detection is a crucial element in the hand-pose estimation and hand-gesture recognition processes in Human-Computer Interaction applications. Most methods use horizontal parallel lines to scan for the location of a wrist line. The challenging problems in wrist detection are determining the ori...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-02-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157817304913 |
| _version_ | 1811265910795665408 |
|---|---|
| author | Andi Sunyoto Agus Harjoko Retantyo Wardoyo Mochamad Hariadi |
| author_facet | Andi Sunyoto Agus Harjoko Retantyo Wardoyo Mochamad Hariadi |
| author_sort | Andi Sunyoto |
| collection | DOAJ |
| description | Wrist detection is a crucial element in the hand-pose estimation and hand-gesture recognition processes in Human-Computer Interaction applications. Most methods use horizontal parallel lines to scan for the location of a wrist line. The challenging problems in wrist detection are determining the orientation and localising the horizontal parallel lines that scan for various hand poses. The proposed method automatically detects a wrist, based on a minimum bounding box and geometric features. It also determines the start and stop points to localise the scanning. The evaluation used a set of 1240 hand images with ground-truth data taken from three sets of data. The hand images contained several gestures and individuals to prove that the method is robust against various gestures. The evaluation shows that the method successfully detects the image orientation and the wrist points with high accuracy. Keywords: Wrist detection, Minimum bounding box, Hand gesture |
| first_indexed | 2024-04-12T20:32:29Z |
| format | Article |
| id | doaj.art-3f589673abdc4553b6924e36e34efc59 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-12T20:32:29Z |
| publishDate | 2020-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-3f589673abdc4553b6924e36e34efc592022-12-22T03:17:41ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782020-02-01322208215Wrist detection based on a minimum bounding box and geometric featuresAndi Sunyoto0Agus Harjoko1Retantyo Wardoyo2Mochamad Hariadi3Department of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta, Indonesia; Department of Computer Science, Universitas AMIKOM Yogyakarta, Indonesia; Corresponding author at: Department of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta, Indonesia.Department of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta, IndonesiaDepartment of Computer Science and Electronics, Universitas Gadjah Mada, Yogyakarta, IndonesiaElectrical Engineering Department, Institut Teknologi Sepuluh Nopember, Surabaya, IndonesiaWrist detection is a crucial element in the hand-pose estimation and hand-gesture recognition processes in Human-Computer Interaction applications. Most methods use horizontal parallel lines to scan for the location of a wrist line. The challenging problems in wrist detection are determining the orientation and localising the horizontal parallel lines that scan for various hand poses. The proposed method automatically detects a wrist, based on a minimum bounding box and geometric features. It also determines the start and stop points to localise the scanning. The evaluation used a set of 1240 hand images with ground-truth data taken from three sets of data. The hand images contained several gestures and individuals to prove that the method is robust against various gestures. The evaluation shows that the method successfully detects the image orientation and the wrist points with high accuracy. Keywords: Wrist detection, Minimum bounding box, Hand gesturehttp://www.sciencedirect.com/science/article/pii/S1319157817304913 |
| spellingShingle | Andi Sunyoto Agus Harjoko Retantyo Wardoyo Mochamad Hariadi Wrist detection based on a minimum bounding box and geometric features Journal of King Saud University: Computer and Information Sciences |
| title | Wrist detection based on a minimum bounding box and geometric features |
| title_full | Wrist detection based on a minimum bounding box and geometric features |
| title_fullStr | Wrist detection based on a minimum bounding box and geometric features |
| title_full_unstemmed | Wrist detection based on a minimum bounding box and geometric features |
| title_short | Wrist detection based on a minimum bounding box and geometric features |
| title_sort | wrist detection based on a minimum bounding box and geometric features |
| url | http://www.sciencedirect.com/science/article/pii/S1319157817304913 |
| work_keys_str_mv | AT andisunyoto wristdetectionbasedonaminimumboundingboxandgeometricfeatures AT agusharjoko wristdetectionbasedonaminimumboundingboxandgeometricfeatures AT retantyowardoyo wristdetectionbasedonaminimumboundingboxandgeometricfeatures AT mochamadhariadi wristdetectionbasedonaminimumboundingboxandgeometricfeatures |