Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM
This paper describes an intelligent algorithm for traffic sign recognition which converges quickly, is accurate in its segmentation and adaptive in its behaviour. The proposed approach can segment images of traffic signs in different lighting and environmental conditions and in different countries....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2011-04-01
|
| Series: | Journal of Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jisys.2011.002 |
| _version_ | 1819121958885785600 |
|---|---|
| author | Fleyeh Hasan Bin Mumtaz Al-Hasanat R. M. |
| author_facet | Fleyeh Hasan Bin Mumtaz Al-Hasanat R. M. |
| author_sort | Fleyeh Hasan |
| collection | DOAJ |
| description | This paper describes an intelligent algorithm for traffic sign recognition which converges quickly, is accurate in its segmentation and adaptive in its behaviour. The proposed approach can segment images of traffic signs in different lighting and environmental conditions and in different countries. It is based on using Kohonen's Self-Organizing Maps (SOM) as a clustering tool and it is developed for Intelligent Vehicle applications. The current approach does not need any prior training. Instead, a slight portion, which is about 1% of the image under investigation, is used for training. This is a key issue to ensure fast convergence and high adaptability. The current approach was tested by using 442 images which were collected under different environmental conditions and from different countries. The proposed approach shows promising results; good improvement of 73% is observed in faded traffic sign images compared with 53.3% using the traditional algorithm. The adaptability of the system is evident from the segmentation of the traffic sign images from various countries where the result is 96% for the nine countries included in the test. |
| first_indexed | 2024-12-22T06:44:50Z |
| format | Article |
| id | doaj.art-1434ae58f87b427bad469de7edb2f374 |
| institution | Directory Open Access Journal |
| issn | 0334-1860 2191-026X |
| language | English |
| last_indexed | 2024-12-22T06:44:50Z |
| publishDate | 2011-04-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Intelligent Systems |
| spelling | doaj.art-1434ae58f87b427bad469de7edb2f3742022-12-21T18:35:19ZengDe GruyterJournal of Intelligent Systems0334-18602191-026X2011-04-01201153110.1515/jisys.2011.002Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOMFleyeh Hasan0Bin Mumtaz Al-Hasanat R. M.1Department of Computer Engineering, School of Technology and Business Studies, Dalarna University, Borlänge, Sweden.Department of Computer Engineering, School of Technology and Business Studies, Dalarna University, Borlänge, Sweden.This paper describes an intelligent algorithm for traffic sign recognition which converges quickly, is accurate in its segmentation and adaptive in its behaviour. The proposed approach can segment images of traffic signs in different lighting and environmental conditions and in different countries. It is based on using Kohonen's Self-Organizing Maps (SOM) as a clustering tool and it is developed for Intelligent Vehicle applications. The current approach does not need any prior training. Instead, a slight portion, which is about 1% of the image under investigation, is used for training. This is a key issue to ensure fast convergence and high adaptability. The current approach was tested by using 442 images which were collected under different environmental conditions and from different countries. The proposed approach shows promising results; good improvement of 73% is observed in faded traffic sign images compared with 53.3% using the traditional algorithm. The adaptability of the system is evident from the segmentation of the traffic sign images from various countries where the result is 96% for the nine countries included in the test.https://doi.org/10.1515/jisys.2011.002colour segmentationneural networkstraffic signsrecognitionclassificationsom |
| spellingShingle | Fleyeh Hasan Bin Mumtaz Al-Hasanat R. M. Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM Journal of Intelligent Systems colour segmentation neural networks traffic signs recognition classification som |
| title | Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM |
| title_full | Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM |
| title_fullStr | Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM |
| title_full_unstemmed | Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM |
| title_short | Adaptive Shadow and Highlight Invariant Colour Segmentation for Traffic Sign Recognition Based on Kohonen SOM |
| title_sort | adaptive shadow and highlight invariant colour segmentation for traffic sign recognition based on kohonen som |
| topic | colour segmentation neural networks traffic signs recognition classification som |
| url | https://doi.org/10.1515/jisys.2011.002 |
| work_keys_str_mv | AT fleyehhasan adaptiveshadowandhighlightinvariantcoloursegmentationfortrafficsignrecognitionbasedonkohonensom AT binmumtazalhasanatrm adaptiveshadowandhighlightinvariantcoloursegmentationfortrafficsignrecognitionbasedonkohonensom |