Cognitive Number Plate Recognition using Machine Learning and Data Visualization Techniques

The conventional Automatic Number Plate Recognition (ANPR) is based on image processing mechanism for automatic vehicle authentication using number plate of a vehicle. The applications of number plate recognition include identification and prevention of vehicular crime, traffic management and handling road challan process. However, APNR exhibits incompetent in case of poor plate localization, improper plate sizing and plate disorientation. Moreover, the ANPR algorithms such Optical character recognition, geometric analysis and character segmentation mechanism less efficient in adverse conditions such as illumination flare on the number plate. Hence, this work presents Cognitive Number Plate Recognition (CNPR) system based on Machine Learning techniques and Data Visualization methods. The proposed system performs knowledge generation through data clustering mechanism. Further, the hidden information pattern within the database of detected number plates is used to provide insight into the vehicle information towards decision making and analysis. The experimentation results of the proposed system show 85.3% of from plate recognition, 90.5% for rear plate, 83.2% of localization and 80.5 % of character segmentation and 73.4 % of character recognition.