Automatic Number Plate Recognition on android platform: With some Java code excerpts
Automatic Number Plate Recognition (ANPR) is an intelligent system which has the capability to recognize the character on vehicle number plate. It is a combination of hardware and software designed to offer the optimum reliability. Since the past decades, many researches have been conducted to recog...
| Main Authors: | , , |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
LAP : LAMBERT Academic Publishing
2016
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/52648/ http://irep.iium.edu.my/52648/ http://irep.iium.edu.my/52648/1/52648_Automatic%20number%20plate%20recognition%20on%20android%20platform.pdf |
| Summary: | Automatic Number Plate Recognition (ANPR) is an intelligent system which has the capability to recognize the character on vehicle number plate. It is a combination of hardware and software designed to offer the optimum reliability. Since the past decades, many researches have been conducted to recognize the vehicle number plate and implemented it in various access control, law enforcement and security, namely parking management system, toll gate access, border access, tracking of stolen vehicles and traffic violations (speed trap). However, previous researches implemented ANPR system on personal computer (PC) with high resolution camera and high computational capability. On the other hand, not many researches have been conducted on the design and implementation of ANPR in mobile phone platforms which have limited camera resolution and processing speed. The main challenges of implementing ANPR algorithm on mobile phone are how to produce a higher coding efficiency, lower computational complexity, and higher scalability. Hence, the objective of this research is to propose suitable and optimize algorithm for ANPR system on Android mobile phone. In this book, various steps to optimize ANPR were described, such as pre-processing, segmentation, and optical character recognition (OCR) using template matching. The proposed ANPR algorithm was based on an open source image processing library called Leptonica and OCR library called Tesseract. For comparison purposes, the template matching based OCR will be compared to Artificial Neural Network (ANN) based OCR. The optimization on ANPR was performed on the pre-processing step using our own Java code as currently there is no image processing library available on the standard Android mobile phone. Performance of the proposed algorithm was evaluated on the developed number plates’ image database captured by mobile phone’s camera, i.e. 30 images. Results showed that the recognition rate and processing time of the proposed algorithm using template matching was 97.46% and 1.13 seconds, respectively. On the other hand, the traditional algorithm using template matching only obtained 83.65% recognition rate with 0.97 second processing time. It shows that our proposed algorithm improved the recognition rate with negligible additional processing time. |
|---|