Prototyping presentation
- 3. Amara Jamal Ibtihaj Uddin Jaweria Nadeem Khan
- 4. Supervisor
- 6. Overview
- 7. Overview ● Today, we are on the cusp of a new automation era: rapid advances in robotics, artificial intelligence, and machine learning are enabling machines to match or outperform humans in a range of work activities, including ones requiring cognitive capabilities. ● Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of images. ● Computer vision is used in many different areas. One of them is image and video processing for purposes of object detection in these images or video files ● Nowadays, very common application of object detection in images is detection of car license plates. This brings us to our project:
- 8. What does Vision do? 01 Vision functions to automatically capture an image of the vehicle’s license plate, 02 Transforms that image into alphanumeric characters using optical character recognition 03 Saves the entries into databases and compare the plate number acquired to one or more databases of vehicles of interest to law enforcement and other agencies.
- 9. Objective
- 10. The purpose of Vision is to introduce a proper solution for car license plate detection used for access restriction and monitoring cars accessing the parking area through the entrance ramp. The main objective of Vision is fast detection of license plates in case of concrete image frames. This automatic number plate recognition can be used to store the images captured by the cameras as well as the text from the license plate.
- 11. Applications
- 12. Target audience/Applications Theft Control/Anti-Crime Parking tickets Highway tolling Petrol stations Access control Airport security
- 14. Vision In Pakistan The technique of using ALPR for surveillance is already proposed by Lahore Police to help them in catching criminals.
- 16. Logical structure Our main objective is to have Accelerated Real Time Image Processing which is a combination of both image enhancement and image detection algorithms to help the security systems.
- 18. System Overview Our system consists of the following units: ● Camera(s) ● Illumination ● Frame grabber ● Computer ● Software ● Hardware ● Database
- 19. Cycle Diagram
- 20. Cycle diagram Image Acquisition Image enhancement Compare and save in database Character Recognition 01 02 03 04
- 21. Problems
- 22. Problems There are a number of possible difficulties that the software must be able to cope with. These include: ● Poor file resolution, usually because the plate is too far away but sometimes resulting from the use of a low-quality camera. ● Blurry images, particularly motion blur. ● Poor lighting and low contrast due to overexposure, reflection or shadows. ● An object obscuring (part of) the plate, quite often a tow bar, or dirt on the plate. ● Vehicle lane change in the camera's angle of view during license plate reading. ● Circumvention techniques. ● Lack of coordination between countries or states. Two cars from different countries or states can have the same number but different design of the plate.
- 23. Camera Positioning, Illumination and Angles Accuracy degrades beyond a 30-degree horizontal or vertical angle. If possible mount the camera high enough and angled slightly downward so as to avoid direct headlight/taillight glare.
- 24. Hardware Design
- 25. Hardware Design 1. Resolution/Frame Rate 2. Compression = 20. A lower 3. Zipstream = Off 4. Camera Capture Mode 5. Image Appearance 6. White Balance 7. Wide Dynamic Range 8. Exposure Settings 9. Image Settings 10. Day/Night 11. IR Illumination
- 26. Result
- 27. Result As shown in the image the result is displayed in the way where it gives all the relevant information about the car including its number plate , make, model , region, etc and all this data is saved in our database. The algorithm for this product is designed in a way that it is efficient enough to not only detect the car but also give relevant information about it so that it is easy to keep all the record and most importantly for the security measure.
- 28. Conclusion
- 29. Conclusion Vision functions to automatically capture an image of the vehicle’s license plate, transform that image into alphanumeric characters using optical character recognition or similar software, compare the plate number acquired to one or more databases of vehicles of interest to law enforcement and other agencies, and to alert the officer when a vehicle of interest has been observed.
- 30. Thank you!