Publication:
Recognizing malaysia traffic signs with pre-trained deep convolutional neural networks

Simple item page
dc.citedby2
dc.contributor.authorHow D.N.T.en_US
dc.contributor.authorSahari K.S.M.en_US
dc.contributor.authorHou Y.C.en_US
dc.contributor.authorBasubeit O.G.S.en_US
dc.contributor.authorid57212923888en_US
dc.contributor.authorid57218170038en_US
dc.contributor.authorid37067465000en_US
dc.contributor.authorid57216623220en_US
dc.date.accessioned2023-05-29T07:23:39Z
dc.date.available2023-05-29T07:23:39Z
dc.date.issued2019
dc.descriptionAgricultural robots; Autonomous vehicles; Convolution; Convolutional neural networks; Deep learning; Deep neural networks; Image recognition; Learning systems; Robotics; Transfer learning; Computer vision techniques; Detection methods; Different class; Feature-based; Learning methods; Learning techniques; Traffic junctions; Traffic sign recognition; Traffic signsen_US
dc.description.abstractAn essential component in the race towards the self-driving car is automatic traffic sign recognition. The capability to automatically recognize road signs allow self-driving cars to make prompt decisions such as adhering to speed limits, stopping at traffic junctions and so forth. Traditionally, feature-based computer vision techniques were employed to recognize traffic signs. However, recent advancements in deep learning techniques have shown to outperform traditional color and shape based detection methods. Deep convolutional neural network (DCNN) is a class of deep learning method that is most commonly applied to vision-related tasks such as traffic sign recognition. For DCNN to work well, it is imperative that the algorithm is given a vast amount of training data. However, due to the scarcity of a curated dataset of the Malaysian traffic signs, training DCNN to perform well can be very challenging. In this demonstrate that DCNN can be trained with little training data with excellent accuracy by using transfer learning. We retrain various pre-trained DCNN from other image recognition tasks by fine-tuning only the top layers on our dataset. Experiment results confirm that by using as little as 100 image samples for 5 different classes, we are able to classify hitherto traffic signs with above 90% accuracy for most pre-trained models and 98.33% for the DenseNet169 pre-trained model. � 2019 IEEE.en_US
dc.description.natureFinalen_US
dc.identifier.ArtNo9058837
dc.identifier.doi10.1109/CRC.2019.00030
dc.identifier.epage113
dc.identifier.scopus2-s2.0-85084071834
dc.identifier.spage109
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85084071834&doi=10.1109%2fCRC.2019.00030&partnerID=40&md5=3da8be6f2d2afd16c62e7bc204c79fa8
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/24455
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.sourceScopus
dc.sourcetitleProceedings - 2019 4th International Conference on Control, Robotics and Cybernetics, CRC 2019
dc.titleRecognizing malaysia traffic signs with pre-trained deep convolutional neural networksen_US
dc.typeConference Paperen_US
dspace.entity.typePublication
Files
Collections
SCOPUS