Downloads: 128 | Views: 262

M.Tech / M.E / PhD Thesis | Electronics & Communication Engineering | India | Volume 4 Issue 8, August 2015 | Popularity: 6.7 / 10

Rate This Article!      

Identification Classification and Monitoring of Traffic Sign Using HOG and Neural Networks

Karthik B, Hari Krishna Murthy, Mukul Manohar

Abstract: When the driving safety is considered, Identification of Traffic sign plays a major role which results in reducing the accidents. The recognition of traffic sign can also be used in Self driving intelligent cars. This paper represents a method to Identify the Traffic sign Patterns using Histogram of Oriented Gradients and Neural Network. Initially a classification of traffic sign is done by using HOG based Support Vector Machine. Secondly the classified data is used to train the Neural Network so that the neural networks are used to recognize the traffic sign patterns.16 different traffic sign image is taken to classify. To check the robustness of this system it was tested against 2, 946 images. It was found that accuracy of recognition was 98 % which indicates clearly the high robustness of the system.

Keywords: Traffic sign, Histogram of Orient Gradient HOG, Support Vector Machine SVM, Artificial Neural Network ANN

Edition: Volume 4 Issue 8, August 2015

Pages: 782 - 786

Make Sure to Disable the Pop-Up Blocker of Web Browser

Click to Cite this Article

Similar Articles