|
| S. no. | Author, year | Technique | Objective and outcome |
|
| 1 | Tran et al., 2020 [28] | 3 DCNN | Fingertip detection with hand gesture recognition was achieved with good accuracy levels for recognition of the patterns on a big dataset |
| 2 | Huang et al., 2019 [22] | Skin detection and deep learning | Firstly detects the skin followed by contour and segment recognition and finally gesture identification for various 10 symbols |
| 3 | Fhager et al., 2019 [21] | Pulsed radar and CNN | Framed time envelope scheme is used to represent data, and further machine learning operations are performed to extract gesture information |
| 4 | Aly et al., 2019 [20] | Deep learning and PCA net | The proposed model used principal component analysis for feature selection and SVM for classifying the gestures |
| 5 | Sanchez-Riera et al., 2018 [27] | ICP minimization and deep learning | This article introduces the variability adjustment of hand gestures of different persons with a high degree of accuracy |
| 6 | Lai et al., 2018 [24] | DSP using FSP algorithm | In this work, a real-time hand gesture evaluation system has been proposed. It is also explored for use in volume control and TV channel changing. The work had an accuracy of 94.3% |
| 7 | Ryu et al., 2018 [26] | FCFW and feature analysis | Gesture recognition is performed by FCFW, and a new feature extraction technique is proposed which performs fairly well compared to the existing techniques |
| 8 | Kim et al., 2017 [23] | Ultra-wideband impulse and CNN | Hand gesture cognition is performed using ultra-wideband impulse sensors in this work. The model predicts 6 hand gestures with 90% accuracy |
| 9 | Chen et al., 2014 [29] | Background subtraction technique | Used the background subtraction method for gesture recognition on a dataset of 1300 images |
| 10 | Lee and Tanaka, 2013 [25] | Depth-based hand recognition | Evaluated 6 hand gestures with volunteers and achieved an accuracy of nearly 91% for the recognition of gestures |
|
