An efficient traffic sign recognition based on graph embedding features

Gudigar, Anjan and Chokkadi, Shreesha and Raghavendra, U and Acharya, Rajendra U (2019) An efficient traffic sign recognition based on graph embedding features. Neural Computing and Applications, 31 (2). pp. 395-407. ISSN 0941-0643

[img] PDF
6234.pdf - Published Version
Restricted to Registered users only

Download (1MB) | Request a copy


Traffic sign recognition (TSR) is one of the significant modules of an intelligent transportation system. It instantly assists the drivers to efficiently recognize the traffic sign. Recognition of traffic sign is a large-scale feature learning problem with different real-world appearances. The main goal of this paper is to develop an efficient TSRmethod, which can run on an ordinary personal computer (PC). In the proposed method, GIST descriptors of the traffic sign images are extracted and subjected to graph-based linear discriminant analysis to reduce the dimension. Moreover, it effectively learns the discriminative subspace through the graph structure with increased computational efficiency. An efficient TSR module is built by conducting series of experiments using support vector machine, extreme learning machine, and knearest neighbor (k-NN) classifiers on available public datasets. Our approach achieved the highest recognition accuracy of 96.33 and 97.79%using k-NNclassifier for German Traffic Sign Recognition Benchmark (GTSRB) and Belgium Traffic Sign Classification Benchmark (BelgiumTSC), respectively. Also it achieved 99.1%accuracy for a subcategory ofGTSRB traffic signs and able to predict the class of unknown traffic sign within 0.0019 s on an ordinary PC. Hence, it can be used in real-world driver assistance system.

Item Type: Article
Uncontrolled Keywords: Computer vision � Intelligent transportation system � Feature selection � GIST � Real-world driver assistance system � Traffic sign recognition
Subjects: Engineering > MIT Manipal > Instrumentation and Control
Depositing User: MIT Library
Date Deposited: 09 Mar 2019 04:23
Last Modified: 09 Mar 2019 04:23

Actions (login required)

View Item View Item