Week 1

Allocation of Roles and Analysis:

During the initial week of our project, our team held a discussion to delegate specific roles and responsibilities to each member. After that, we defined the project requirements and outlined the software architecture.

Lab Day:

Today, our original task was to solve the hardware problem, but when we arrived at the lab, we found that we had no materials for our group, so we gave priority to the research and discussion of the software problem.

The components we needed included:

So we shifted our focus this week to software. We successfully implemented the core functionality of the recognition algorithm and completed the coding phase. However, during testing, we encountered some problems.

In the first week of our project, we focused on developing a license plate recognition system using traditional computer vision techniques. Our initial approach relied on OpenCV, a widely used library for image processing. Instead of utilizing deep learning models, we opted for classical image processing techniques such as Gaussian noise reduction, color filtering, binarization, morphological transformations, and edge detection. These methods are computationally efficient and do not require extensive labeled datasets for training, making them an attractive choice for real-time applications.

Methods and Techniques Used

1. Gaussian Noise Reduction

2. Color Filtering

3. Binarization

4. Morphological Transformations

5. Edge Detection

Challenges Encountered

Color Filtering Limitations: 

One major issue arose when detecting white-colored license plates. The effectiveness of color filtering was significantly reduced, as white plates blended with other bright areas in the image, making segmentation difficult.

Varying License Plate Colors: 

Based on our research, we found that many license plates follow a pattern where the front plate is white while the rear plate is yellow. This inconsistency created additional challenges in applying uniform color filtering rules.

Next Week

• Improve Color Filtering: By incorporating adaptive color detection techniques that adjust to different lighting conditions and license plate colors.

• Enhance Feature Extraction: Experimenting with contour detection and shape recognition to better identify license plates in diverse conditions.

• Explore Hybrid Methods: Considering a combination of classical computer vision and deep leaning.