A comparison between end-to-end approaches and feature extraction based approaches for Sign Language recognition
Oliveira, MarlonORCID: 0000-0003-0528-3807, Chatbri, Houssem, Little, SuzanneORCID: 0000-0003-3281-3471, O'Connor, Noel E.ORCID: 0000-0002-4033-9135 and Sutherland, Alistair
(2018)
A comparison between end-to-end approaches and feature extraction based approaches for Sign Language recognition.
In: Image and Vision Computing New Zealand 2017 (IVCNZ), 4-6 Dec 2017, Christchurch, New Zealand.
In this work we use a new image dataset for Irish Sign Language (ISL) and we compare different approaches for recognition. We perform experiments and report comparative accuracy and timing. We perform tests over blurred images and compare results with non-blurred images. For classification, we use end-to-end approach, such as Convolutional Neural Networks (CNN) and feature based extraction approaches, such as Principal Component Analysis (PCA) followed by different classifiers, i.e. multilayer perceptron (MLP). We obtain a recognition accuracy over 99% for both approaches. In addition, we report different ways to split the training and testing dataset, being one iterative and the other one random selected.
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Conference
Refereed:
Yes
Uncontrolled Keywords:
handshape recognition; machine learning; pattern recognition; sign language
2017 International Conference on Image and Vision Computing New Zealand (IVCNZ). Image and Vision Computing New Zealand, IVCNZ, International Conference
.
IEEE Computer Society.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
CAPES/Brazilian Science without Borders, process no.: 9064-13-3, European Regional Development Fund, IRC under Grant no. GOIPD/2016/61, SFI under Grant no. SFI/12/RC/2289 (Insight)
ID Code:
22132
Deposited On:
07 Dec 2017 12:49 by
Houssem Chatbri
. Last Modified 07 Feb 2019 10:34