Show simple item record

dc.contributor.authorBiswas, Rubel
dc.contributor.authorTora, Moumita Roy
dc.contributor.authorBhuiyan, Farazul Haque
dc.date.accessioned2017-01-04T05:16:16Z
dc.date.available2017-01-04T05:16:16Z
dc.date.issued2014
dc.identifier.citationBiswas, R., Tora, M. R., & Bhuiyan, F. H. (2014). LVQ and HOG based speed limit traffic signs detection and categorization. Paper presented at the 2014 International Conference on Informatics, Electronics and Vision, ICIEV 2014, doi:10.1109/ICIEV.2014.6850741en_US
dc.identifier.isbn978-147995179-6
dc.identifier.urihttp://hdl.handle.net/10361/7508
dc.descriptionThis conference paper was presented in the International Conference on Informatics, Electronics and Vision, ICIEV 2014; Dhaka; Bangladesh; 23 May 2014 through 24 May 2014 [© 2014 IEEE] The conference paper's definite version is available at: http://dx.doi.org/10.1109/ICIEV.2014.6850741en_US
dc.description.abstractThe proper identification of the traffic signs can ensure driving safety and can play a very important role in reducing the number of road accidents significantly. This paper represents a uniform way to detect the speed limit traffic signs and to confirm it by recognizing the sign's speed number. In this system, firstly the red color objects are segmented from an image using LVQ. Secondly, detected circular part is extracted from the color segmented image using bounding box and then Histogram Oriented Gradient (HOG) is used to collect the feature of the extracted part of circular object and finally SVM classifier is applied to train the HOG features of each speed no. into their corresponding classes. In general, the system detects the prohibitory traffic sign in the first place, specifies whether the detected sign is a speed limit sign, and then determines the allowed speed in case the detected sign is a speed limit sign. The SVM classifier was trained with 200 images which were collected in different light conditions. To check the robustness of this system, it was tested against 381 images which contain 361 Speed Limit traffic sign and 30 Non- Speed Limit signs. It was found that the accuracy of recognition was 92.75% which indicates clearly the high robustness targeted by this system.en_US
dc.language.isoenen_US
dc.publisher© 2014 IEEE Computer Societyen_US
dc.relation.urihttp://ieeexplore.ieee.org/document/6850741/
dc.subjectCircular hough transformen_US
dc.subjectHOGen_US
dc.subjectLVQen_US
dc.subjectSVMen_US
dc.subjectTraffic signen_US
dc.titleLVQ and HOG based speed limit traffic signs detection and categorizationen_US
dc.typeConference paperen_US
dc.description.versionPublished
dc.contributor.departmentDepartment of Computer Science and Engineering, BRAC University
dc.identifier.doihttp://dx.doi.org/10.1109/ICIEV.2014.6850741


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record