Using grayscale images for object recognition with convolutional-recursive neural network

Bui, H, Lech, M, Cheng, E, Neville, K and Burnett, I 2016, 'Using grayscale images for object recognition with convolutional-recursive neural network', in Proceedings of the 2016 IEEE Sixth International Conference on Communications and Electronics (ICCE 2016), Ha Long, Vietnam, 27-29 July 2016, pp. 321-325.


Document type: Conference Paper
Collection: Conference Papers

Title Using grayscale images for object recognition with convolutional-recursive neural network
Author(s) Bui, H
Lech, M
Cheng, E
Neville, K
Burnett, I
Year 2016
Conference name ICCE 2016
Conference location Ha Long, Vietnam
Conference dates 27-29 July 2016
Proceedings title Proceedings of the 2016 IEEE Sixth International Conference on Communications and Electronics (ICCE 2016)
Publisher IEEE
Place of publication United States
Start page 321
End page 325
Total pages 5
Abstract There is a common tendency in object recognition research to accumulate large volumes of image features to improve performance. However, whether using more information contributes to higher accuracy is still controversial given the increased computational cost. This work investigates the performance of grayscale images compared to RGB counterparts for visual object classification. A comparison between object recognition based on RGB images and RGB images converted to grayscale was conducted using a cascaded CNN-RNN neural network structure, and compared with other types of commonly used classifiers such as Random Forest, SVM and SP-HMP. Experimental results showed that classification with grayscale images resulted in higher accuracy classification than with RGB images across the different types of classifiers. Results also demonstrated that utilizing a small receptive field CNN and edgy feature selection on grayscale images can result in higher classification accuracy with the advantage of reduced computational cost.
Subjects Electrical and Electronic Engineering not elsewhere classified
Computer Vision
Keyword(s) machine learning
object recognition
convolutional
neural network
image classification
DOI - identifier 10.1109/CCE.2016.7562656
Copyright notice © 2016 IEEE
ISBN 9781509018024
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 1 times in Scopus Article | Citations
Altmetric details:
Access Statistics: 186 Abstract Views  -  Detailed Statistics
Created: Thu, 17 Nov 2016, 09:24:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us