1. Type of Vehicle Recognition Using Template Matching Method Electrical Engineering Department Petra Christian University Surabaya - Indonesia Thiang, Andre Teguh Guntoro, Resmana Lim

2. Agenda of Presentation  Introduction  Object Detection  Object Segmentation  Matching  Experiment Result  Discussion and Conclusion

3. Introduction  Purpose: To recognize type of car that enter to park area  Three types of car: sedan, van and pickup  Using a simple matching method  Using a camera as a sensor to recognize type of car visually Overview of this research

4. Introduction Block Diagram of System

5. Object Detection Image Preprocessing  Converting image from RGB to gray scale  Histogram Equalization There are three processes This process will adjust brightness and contrast of image

6. Object Detection Image Preprocessing  Noise removal process using low pass filter with 3x3 neighborhood Where is low pass filter kernel

7. Object Detection  It is done in predefined area of the image  To detect the existence of the car, the system will substract background image from the image Object detection area and its result

8. Object Segmentation There are two stages in this process  Discard background of the image, so it will show the object only and then morphology operation  Seek the optimal position of object in the image It is done by substract background image from the image It is done by calculate the cumulative histogram value for each possible existence object in the image

9. Object Segmentation Object, object segmentation area and its result

10. Matching Template matching  Compare the image with several template image  The image and template image must has the same dimension  Identifying type of the car using the highest similarity value  The image will have similarity value for each template image Similarity Equation

11. Experiment Result  There are 12 images for template image  Similarity value varies from 0.78124 to 0.93988  Template matching results high similarity value for image that similar to its template, but it will also happen to other images

12. Experiment Result

13. Discussion and Conclusion  Template matching method gives a good result in recognizing the type of the car  It results high similarity value for image that similar to its template, but it will also happen to other images those are not similar to the template at all  For the next step, this method can be combined to feature extraction method like gabor filter to get a better result