| Download | - View final version: Long Hands gesture recognition system: 2 step gesture recognition with machine learning and geometric shape analysis (PDF, 3.9 MiB)
|
|---|
| DOI | Resolve DOI: https://doi.org/10.1007/s11042-022-12870-8 |
|---|
| Author | Search for: Popov, Pavel A.1ORCID identifier: https://orcid.org/0000-0003-1127-0842; Search for: Laganière, RobertORCID identifier: https://orcid.org/0000-0001-9475-8151 |
|---|
| Affiliation | - National Research Council of Canada
|
|---|
| Format | Text, Article |
|---|
| Subject | adaboost; adaptive colour segmentation; contour shape analysis; hand gesture recognition; HOG; MobileNets; neural network; shape signature; SVM |
|---|
| Abstract | A two stage real-time hand gesture recognition system is presented. It combines a machine learning trained detection step with a colour processing contour shape validation step. The detection step is done with either Adaboost Cascades or Support Vector Machines using HOG features. The system achieves a low false positive rate and a sufficient true positive rate necessary for robust real-time performance. It performs well compared to MobileNets a state of the art Neural Network for mobile real-time applications. |
|---|
| Publication date | 2022-11 |
|---|
| Publisher | Scopus |
|---|
| Licence | |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Identifier | 12870 |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 9141bcec-0863-4278-ae73-88d333f12c76 |
|---|
| Record created | 2024-02-27 |
|---|
| Record modified | 2024-02-27 |
|---|
