Secured Toll Surveillance System through Combination of KNN, Outguess and DES

? Abstract— Automatic Number Plate Recognition is a real time embedded system which automatically recognizes the license number of vehicles. In this project, the implementation of recognizing number plate is considered. After recognizing the characters from number plate by implementing various algorithms, the characters are transmitted through secure channel. For secure transmission of recognized characters i.e. vehicle number, Steganography techniques are used. First characters are encrypted by using DES algorithm, after that these encrypted characters are embedded into the image by using outguess algorithm. At the receiver end this embedded data is extracted. Extensive experimentation has been performed in order to estimate the best parameters for the task at hand, and the results obtained are presented. The results of this technique are then reviewed. Finally, possible extension to make the algorithm more robust is discussed