International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056

Volume: 04 Issue: 04 | Apr -2017 www.irjet.net p-ISSN: 2395-0072

A Survey on Road sign Detection and ClassificationMiss. Priyanka A. Nikam1,

Prof.Nitin B. Dhaigude 2
1Student, Dept. of Electronics &Telecommunication, SVPMs COE Malegaon (Bk), Maharashtra, India
2 Assistant Professor, Dept. of Electronics &Telecommunication, SVPMs COE Malegaon (Bk), Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
AbstractTraffic sign recognition plays very important role There are many methods for solving these tasks. Road sign
in driver assistant system to disburden driver as well as in detection is a technique due to which vehicle is able to
intelligent autonomous vehicles. This framework includes two recognize the different signs put on the road. Traffic signs are
parts: traffic sign detection and classification of detected used to regulate traffic. Traffic signs are used to provide
traffic signs. This paper recommends different methods for guidance to driver. Automatic traffic sign recognition is
detection and recognition of traffic signs. Different methods essential task of traffic regulation and guiding and warning
are used for traffic sign detection and recognition like color driver.
segmentation, RGB to HSI model. Recognition includes HOG
Generally traffic sign provide the driver very essential
feature, shape context etc.
information for safe and efficient navigation.

Keywords RGB model, HSI model, Hough circle transform,

2. REVIEW OF LITERATURE
shape context, HOG features..
2.1 J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, The
1. INTRODUCTION
German traffic sign recognition benchmark: a multi-class
Traffic sign recognition has high industrial potential in
classification competition, in Proc. IEEE IJCNN, 2011, pp.
intelligent autonomous vehicle and driver assistance
14531460.
system.improvement in traffic quality and safety cannot be
achieved without correctly applying and maintaining road This paper proposes the design and analysis of the
traffic signs, traffic signals and road markings. The traffic German Traffic Sign Recognition Benchmark dataset and

indication sign recognition is essential to the ITS (Intelligent competition. The results of the competition show that state-
Transport System). Every year 1.3 million people worldwide of-the-art machine learning algorithms perform very good in
are killed on roads, and between 20 and 40 million are the challenging task of traffic sign recognition. The
injured. A good solution to this problem would be to develop participants achieved a very high performance of up to
system, which take into account the environment. That is why 98.98% correct recognition rate which is similar to human
today, driving safety is becoming a popular topic in many performance on this dataset.
fields, from small projects to large car factories. However this
2.2 S. Houben, J. Stallkamp, J. Salmen,M. Schlipsing, and C.
topic also raises many questions and problems. It is required
Igel, Detection of traffic signs in real-world images: The
to define the width of the edges of the road, recognize road
German traffic sign detection benchmark, in Proc. IEEE
signs, traffic lights, pedestrians, and other objects which
IJCNN, 2013, pp. 18.
contribute the driving safely.

2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2347
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017 www.irjet.net p-ISSN: 2395-0072

This paper proposes a real-world benchmark data 2.4Traffic indication symbols recognition with shape
set for traffic sign detection together with carefully chosen context by Kai Li, Weiyao Lan, Department of
evaluation metrics, baseline results, and a web-interface for Automation Xiamen University, China, 2011, IEEE
comparing approaches. In their evaluation, they separate
In this paper to detect the traffic sign, HIS color
sign detection from classification, also measured the
model followed by circle detection is used. The regions
performance on relevant categories of signs to allow for
detected by color detection cannot be determined to the
benchmarking specialized solutions. The considered baseline
exact sign region. In this method the edge of interested
algorithms represent some of the most well liked detection
regions is traced to get their contours after morphologic
approaches such as the Viola-Jones detector based on Haar
operations. Then to find the target region, Hough circle
features and a linear classifier relying on HOG descriptors.
transform is applied. The object have been detected and
Further, a recently proposed problem-specific algorithm
extracted after the previous two steps. We next recognize the
utilizing shape and color in a model-based Hough like voting
symbol in the destination area. The image is preprocessed to
scheme is evaluated.
remove noise. To obtain a clear silhouette boundary of the
2.3Towards Real-Time Traffic Sign Detection and traffic indication symbol Edge detection and segmentation
Classification by Yi Yang, Hengliang Luo, Huarong Xu and are used specifically to the image. Shape context is based on
Fuchao Wu,2014, IEEE. the contour of the object.

This paper points to deal with real-time traffic sign 2.5 Real-Time Detection and Recognition of Road Traffic
recognition, i.e. localizing what type of traffic sign appears in Signs by Jack Greenhalgh and Majid Mirmehdi, Senior
which area of an input image at a fast processing time. To Member, 2012, IEEE
achieve this objective, a two-module framework (detection
This paper aims to deal with novel system for the
module and classification module) is proposed. In detection
automatic detection and recognition of traffic signs.
module, the input color image is transformed to probability
Candidate regions are detected as maximally stable extremal
maps by using color probability model. Then the road sign
regions (MSERs), which offers ruggedness to variations in
proposals are extracted by finding maximally stable extremal
lighting Conditions. Recognition is based on a cascade of
regions on these maps. Lastly , an SVM classifier which
support vector machine (SVM) classifiers that were trained
prepare with color HOG features is used to further filter out
using histogram of oriented gradient (HOG) features. This
the false positives and classify the present proposals to their
system is accurate at high vehicle speeds, operates under a
super classes. In classification module, they used CNN to
range of weather conditions, runs at an average speed of 20
classify the detected traffic signs to their sub-classes within
frames per second.
each super class. Demonstration on the GTSDB benchmark
shows that their method achieved comparable performance 3.CONCLUSION
to the state-of-the-art methods with outstanding improved
computational efficiency, which is 20 times faster than the Papers discussed above provide various methods for
existing best method. detection and classification of traffic sign. Detection module

2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2348
 International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017 www.irjet.net p-ISSN: 2395-0072

includes color and shape analysis. Classification module

include SVM classifier, edge detection which provides
improved results.it is necessary to have best methods to
provide best result which will significantly improve driving
safety comfort.

REFERENCES

[1] J. Stallkamp, M. Schlipsing, J. Salmen, and C. Igel, The

German traffic sign recognition benchmark: a multi-class
classification competition, in Proc. IEEE IJCNN, 2011, pp.
14531460.

[2] S. Houben, J. Stallkamp, J. Salmen,M. Schlipsing, and C.

Igel, Detection of traffic signs in real-world images: The
German traffic sign detection benchmark, in Proc. IEEE
IJCNN, 2013, pp. 18.

[3] Yi Yang, Hengliang Luo, Huarong Xu and Fuchao Wu,

Towards Real-Time Traffic Sign Detection and
Classification, IEEE,2014.

[4] Kai Li, Weiyao Lan, Traffic indication symbols

recognition with shape context, IEEE ,2011.

[5] J. Greenhalgh and M. Mirmehdi, Real-time detection and

recognition of road traffic signs, IEEE Trans. Int. Transp.
Syst., vol. 13, no. 4, pp. 14981506, Dec. 2012.

2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 2349