@conference { ISI:000346142800010, title = {Detection and recognition of road signs in a video stream based on the shape of the panels.}, booktitle = {2014 9TH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS: THEORIES AND APPLICATIONS (SITA{\textquoteright}14)}, year = {2014}, note = {9th International Conference on Intelligent Systems - Theories and Applications (SITA), Inst Natl Postes \& Telecommunicat, Rabat, MOROCCO, MAY 07-08, 2014}, publisher = {IEEE; IEEE Morocco}, organization = {IEEE; IEEE Morocco}, abstract = {In this paper, we present a robust approach of automatic detection and recognition of road signs in national roads, starting from the images resulting from a video stream taken by a camera embarked on a vehicle. Our approach is composed of three main phases: the first phase is to extract video stream images containing a circle or a triangle. This extraction is performed respectively by Hough transformation and Ramer-Douglas-Peucker filter, the second phase consists of extraction areas of the calculated image, in the previous phase. In the third and last phase, we proceed to a matching of the extracted image areas with signs of reference by comparison of interest points extracted by the SURF method and the matching method FLANN.}, isbn = {978-1-4799-3566-6}, author = {Romadi, Mohammed and Oulahhajthami, Rachid and Romadi, Rahal and Chiheb, Raddouane} } @conference { ISI:000350287800020, title = {Detection and Recognition of Road Signs}, booktitle = {2013 3RD INTERNATIONAL SYMPOSIUM ISKO-MAGHREB}, year = {2013}, note = {ISKO-Maghreb 3rd International Symposium, Marrakech, MOROCCO, NOV 08-09, 2013}, publisher = {ISKO}, organization = {ISKO}, abstract = {In this paper, we present an application for the detection and recognition of Moroccan road signs together with their positions in video sequences taken by a mobile scanning vehicle in rural areas. Our approach is based on processing the operations of pictures: morphology, segmentation, edge detection and object recognition. The application runs on an algorithm which consists of five main steps: input (pre-recording video stream), processing of video keyframes, edge detection, detection of geometric shapes known panels, recognizing the meaning and the position of the panel detected.}, isbn = {978-1-4799-3392-1}, author = {Romadi, Mohammed and Oulad Haj Thami, Rachid and Chiheb, Raddouane and Romadi, Rahal} }