Centre de documentation
scientifique

Using geometric constraints to improve performance of image classifiers for automatic segmentation of traffic signs / Roholah Yazdan in Geomatica, vol 75 n° 1 (Mars 2021)  

Public [article]  inGeomatica > vol 75 n° 1 (Mars 2021) . - pp 28 - 50 Titre : Using geometric constraints to improve performance of image classifiers for automatic segmentation of traffic signs Type de document : Article/Communication Auteurs : Roholah Yazdan, Auteur ; Masood Varshosaz, Auteur ; Saied Pirasteh, Auteur ; Fabio Remondino, Auteur Année de publication : 2021 Article en page(s) : pp 28 - 50 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] contrainte géométrique [Termes IGN] espace colorimétrique [Termes IGN] programmation par contraintes [Termes IGN] signalisation routière Résumé : (auteur) Automatic detection and recognition of traffic signs from images is an important topic in many applications. At first, we segmented the images using a classification algorithm to delineate the areas where the signs are more likely to be found. In this regard, shadows, objects having similar colours, and extreme illumination changes can significantly affect the segmentation results. We propose a new shape-based algorithm to improve the accuracy of the segmentation. The algorithm works by incorporating the sign geometry to filter out the wrong pixels from the classification results. We performed several tests to compare the performance of our algorithm against those obtained by popular techniques such as Support Vector Machine (SVM), K-Means, and K-Nearest Neighbours. In these tests, to overcome the unwanted illumination effects, the images are transformed into colour spaces Hue, Saturation, and Intensity, YUV, normalized red green blue, and Gaussian. Among the traditional techniques used in this study, the best results were obtained with SVM applied to the images transformed into the Gaussian colour space. The comparison results also suggested that by adding the geometric constraints proposed in this study, the quality of sign image segmentation is improved by 10%–25%. We also comparted the SVM classifier enhanced by incorporating the geometry of signs with a U-Shaped deep learning algorithm. Results suggested the performance of both techniques is very close. Perhaps the deep learning results could be improved if a more comprehensive data set is provided. Numéro de notice : A2021-608 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1139/geomat-2020-0010 En ligne : https://doi.org/10.1139/geomat-2020-0010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98322 [article]