ABSTRACT :
In today’s world, almost everything we do has been simplified by automated tasks. In an attempt to focus on the road while driving, drivers often miss out on signs on the side of the road, which could be dangerous for them and for the people around them. This problem can be avoided if there was an efficient way to notify the driver without having them to shift their focus. Traffic Sign Detection and Recognition (TSDR) plays an important role here by detecting and recognizing a sign, thus notifying the driver of any upcoming signs. This not only ensures road safety, but also allows the driver to be at little more ease while driving on tricky or new roads. Another commonly faced problem is not being able to understand the meaning of the sign. With the help of this Advanced Driver Assistance Systems (ADAS) application, drivers will no longer face the problem of understanding what the sign says. In this paper, we propose a method for Traffic Sign Detection and Recognition using image processing for the detection of a sign and an ensemble of Convolutional Neural Networks (CNN) for the recognition of the sign. CNNs have a high recognition rate, thus making it desirable to use for implementing various computer vision tasks. TensorFlow is used for the implementation of the CNN. We have achieved higher than 99% recognition accuracies for circular signs on the Belgium and German data sets.
EXITING SYSTEM :
Nowadays, recognition and classification of traffic signs are very important, especially for unmanned automatic driving. Extensive research has been done in the area of recognition and classification of traffic and road signs. In [1], the authors proposed a Convolutional Neural Network and Support Vector Machines (CNN-SVM) method for traffic signs recognition and classification. The colouring used in this method is YCB Cr colour space which is input to the convolutional neural network to divide the colour channels and extracting some special characteristics. SVM is then used for classification. Their proposed method achieved a 98.6% accuracy for traffic signs recognition and classification. In [2], the authors proposed a colour based segmentation method with Histogram Oriented Gradients (HOG) for feature extraction followed by SVM for classification. The model used CIECAM97 for colour appearance, this model was applied to a segment to extract colour information. Another model used for shape features is FOSTS [3] which achieved a 95% accuracy. In [4], the authors proposed feature extraction through HOG and local binary pattern (LBP) which are then input into an Extreme Learning Machine Network for classification and recognition. In [5], the authors propose a traffic sign recognition system based on extreme learning machine (ELM). Their method consists of feature extraction through extraction of histogram of the oriented gradient variant (HOGV) features followed by a single classifier trained by ELM.
DISADVANTAGES OF EXISTING SYSTEM :
1) Less accuracy
2)low Efficiency
PROPOSED SYSTEM:
The contribution of this paper will be two folds; one is to develop a new database for Arabic Traffic and Road Signs and the other is develop and design a deep CNN architecture for Arabic Traffic sign recognition. Fig. 1 shows the high level view of the system. The collected data set is given as an input to the proposed CNN architecture for training, validation and testing. The detailed explanation of the CNN architecture is provided in the next section. Once the CNN is trained, it is ready to be used for classifying new images which were not part of the collected dataset.
ADVANTAGES OF PROPOSED SYSTEM :
1) High accuracy
2)High efficiency
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
