Development of portable automatic number plate recognition system on android mobile phone
The Automatic Number Plate Recognition (ANPR) System leads the role in utilizing of various access control and security, such as: tracking of stolen vehicles, traffic violations (speed trap) and parking. In this paper, we present the portable ANPR which is implemented on android mobile phone. Since...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/32400/ http://irep.iium.edu.my/32400/ http://irep.iium.edu.my/32400/1/Abdul_ANPR_camera_ready.pdf http://irep.iium.edu.my/32400/4/programbookiec.pdf |
| Summary: | The Automatic Number Plate Recognition (ANPR) System leads the role in utilizing of various access control and security, such as: tracking of stolen vehicles, traffic violations (speed trap) and parking. In this paper, we present the portable ANPR which is implemented on android mobile phone. Since the main challenges in mobile application are higher coding efficiency, reduced computational complexity, and improved flexibility. Thus, the significance efforts are to find suitable and adaptive algorithm for number plate recognition under mobile phone. Namely, optimizing the ANPR system for mobile phone that has limited CPU and memory resources, geo-tagging of the image using GPS coordinates and online database in order to store the vehicle’s information. Here also we discuss the minimum hardware requirement which is android mobile phone that portable ANPR will be implemented. We proposed the following design for portable ANPR on android mobile phone. First, the graphical user interface (GUI) for capturing image using built-in camera was developed to acquire vehicle plate number in Malaysia. Second, the preprocessing of raw image was done using contrast enhancement. Next, character segmentation using fixed pitch and an optical character recognition (OCR) using neural network were utilized to extract texts and numbers. Both character segmentation and OCR are using Tesseract library from Google Inc. The proposed portable ANPR algorithm was implemented and simulated using Android SDK on a computer. Based on the experimental results, the proposed system can effectively recognize the license number at 90.86%. The needed processing time to recognize a license plate is only 2 second. The result is consider good in comparison with the results gained from previous system that processed in desktop PC with the result of range 91.59% to 98% for the recognition accuracy and 0.284 second to 1.5 second for the recognition time. |
|---|