Download presentation
Presentation is loading. Please wait.
Published byAngel Eustacia Adams Modified over 9 years ago
1
License Plate Identification Amir Ali Ahmadi Jonathan Neville Justin Sobota Mehmet Ucal
2
Outline Motivation Previous Work Approach Algorithms –Character Identification –Plate Extraction Results Conclusion/Future Work
3
Motivation Traffic Control Automated Ticketing Finding Stolen Cars High Speed Pursuit
4
Previous Work License Plate Identification/Recognition (LPI/R) –http://www.photocop.com/http://www.photocop.com/ –Retrieves Plate Numbers for All States –Determines Speed –Several vendors Three algorithms for license number extraction
5
Previous Work Template Matching –Compares extracted characters to a set of templates –Very reliable under standard conditions –Viewing angle, Lighting, plate size, etc. can cause errors
6
Previous Work Structural Analysis –Uses geometric features and a decision tree to determine character –Very complex time-consuming analysis Loops? # of Loops Location of Loop? Left Side Straight? B 8 yes 1 2 no top bottom middle 6 D
7
Previous Work Neural Networks –Trained by example –Adapt to characters’ distinctive feature –Performs well in bad conditions
8
Our Approach Template Matching Assumptions –Only white Maryland Plates –Camera angle directly behind car –2 types of MD plates 6 characters with MD logo in center 7 characters
9
Approach Plate Extraction Character Extraction Template Matching Character Identification
10
Character Identification Char. Extract Support Set Extract Comparison Char. Filtering Template Filtering Template Images License Plate Number
11
Template Filtering Templates obtained from actual plates Template Filtering –RGB2Gray –Threshold (Black/White) –Resize Output array of templates
12
Character Extraction Plate resized to predetermined dimensions Output array of extracted characters
13
Character Filtering RGB2Gray Threshold (Black/White) Median Filtering
14
Character Identification Char. Extract Support Set Extract Comparison Char. Filtering Template Filtering Template Images License Plate Number
15
Support Set Extraction Row sums Column sums Exclude low sums Extract largest continuous region Resize to template size
16
Comparison ? ?
17
Approach Plate Extraction Character Extraction Template Matching Character Identification
18
Plate Extraction RGB2Gray Threshold (Black/White) Row/Column means Extract largest continuous white region
19
Results for Character Identification InputOutput License Identification
20
Results for Character Identification InputOutput License Identification
21
Results for Plate Extraction InputOutputPlate Extraction
22
Results for Plate Extraction InputOutputExtracted “M”
23
Failed Plate Extractions InputOutputPlate Extraction
24
Failed Plate Extractions InputOutputPlate Extraction No Extracted Plate No Output
25
Conclusion Template matching approach was taken Algorithm –Plate Extraction –Character Identification Given the plates, we were able to identify almost all of the characters Plate extraction was limited to darker cars
26
Future Work Improve templates to better accommodate the plate characters Refine threshold levels for determining the whiteness in the picture Eliminate issues regarding glare, dirtiness of the plate, shadows, and white regions in the picture Dynamic character extraction –Character position found by the algorithm
27
Demonstration
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.