ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT
Ability to recognise road signs in due time is an essential aspect of safe driving especially at night. Hence an auto road sign recognition system is a desirable add-on to a night vision system. This paper presents the use of affine moment invariants (AMIs) as the invariant feature vectors, and the...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UUM Press
2004-11-01
|
| Series: | Journal of ICT |
| Subjects: | |
| Online Access: | https://e-journal.uum.edu.my/index.php/jict/article/view/8044 |
| _version_ | 1798040933666652160 |
|---|---|
| author | Liong Choong Yeun |
| author_facet | Liong Choong Yeun |
| author_sort | Liong Choong Yeun |
| collection | DOAJ |
| description | Ability to recognise road signs in due time is an essential aspect of safe driving especially at night. Hence an auto road sign recognition system is a desirable add-on to a night vision system. This paper presents the use of affine moment invariants (AMIs) as the invariant feature vectors, and the multilayer perceptron (MLP) neural network as the pattern classifier, in developing a road sign recognition system. Six classes of road signs of different position, size and orientation, which were extracted from various near infra-red (NIR) road scenes, have been processed to validate the system. The first four simple AMIs Iâ‚, - Iâ‚„, were used for the image registration. The AMIs, which were computed from central moments, formed a feature vector that was invariant under the general affine transformation. These feature vectors were then fed into an MLP neural network for classification. The MLP used was trained with the quickprop algorithm (QA), a variation of the standard back-propagation (BPA) algorithm. Scaling and transformation of the feature vectors have reduced its dynamic range significantly towards improving the network convergence and performance. The trained and tested MLP was then validated with a set of feature vectors. This study has achieved a 100% successful classification rate using a limited validation set of road sign images.
|
| first_indexed | 2024-04-11T22:14:31Z |
| format | Article |
| id | doaj.art-42784f5b293f4a26b84c409497ac6f20 |
| institution | Directory Open Access Journal |
| issn | 1675-414X 2180-3862 |
| language | English |
| last_indexed | 2024-04-11T22:14:31Z |
| publishDate | 2004-11-01 |
| publisher | UUM Press |
| record_format | Article |
| series | Journal of ICT |
| spelling | doaj.art-42784f5b293f4a26b84c409497ac6f202022-12-22T04:00:28ZengUUM PressJournal of ICT1675-414X2180-38622004-11-0132ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANTLiong Choong Yeun0School of Mathematical Sciences, Faculty of Science and Technology Universiti Kehangsaan Malaysia, 43600 UKM Bangi, Selangor D.E.Ability to recognise road signs in due time is an essential aspect of safe driving especially at night. Hence an auto road sign recognition system is a desirable add-on to a night vision system. This paper presents the use of affine moment invariants (AMIs) as the invariant feature vectors, and the multilayer perceptron (MLP) neural network as the pattern classifier, in developing a road sign recognition system. Six classes of road signs of different position, size and orientation, which were extracted from various near infra-red (NIR) road scenes, have been processed to validate the system. The first four simple AMIs Iâ‚, - Iâ‚„, were used for the image registration. The AMIs, which were computed from central moments, formed a feature vector that was invariant under the general affine transformation. These feature vectors were then fed into an MLP neural network for classification. The MLP used was trained with the quickprop algorithm (QA), a variation of the standard back-propagation (BPA) algorithm. Scaling and transformation of the feature vectors have reduced its dynamic range significantly towards improving the network convergence and performance. The trained and tested MLP was then validated with a set of feature vectors. This study has achieved a 100% successful classification rate using a limited validation set of road sign images. https://e-journal.uum.edu.my/index.php/jict/article/view/8044Road sign recognitionaffine moment invariants (AMIs)multilayer percepstron (MLP)quickpropquickprop algorithm (QA) |
| spellingShingle | Liong Choong Yeun ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT Journal of ICT Road sign recognition affine moment invariants (AMIs) multilayer percepstron (MLP) quickprop quickprop algorithm (QA) |
| title | ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT |
| title_full | ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT |
| title_fullStr | ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT |
| title_full_unstemmed | ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT |
| title_short | ROAD SIGN RECOGNITION USING AFFINE MOMENT INVARIANT |
| title_sort | road sign recognition using affine moment invariant |
| topic | Road sign recognition affine moment invariants (AMIs) multilayer percepstron (MLP) quickprop quickprop algorithm (QA) |
| url | https://e-journal.uum.edu.my/index.php/jict/article/view/8044 |
| work_keys_str_mv | AT liongchoongyeun roadsignrecognitionusingaffinemomentinvariant |