- Apply specific approach for Pattern Recognition.
- Implement this approach in MATLAB.
- Compare and discuss the results with others.
Project 1: "An Efficient Human Identification Using Gait Analysis" I want apply/follow the same methodology (Methods/Algorithms) for this paper ("Human Gait Recognition Using Bezier Curves" Pratibha Mishra, Shweta Ezra 2011)
- Applying the algorithm which is based on Bezier curves. Bezier curves are generated according to person's walk and recognition is achieved by matching those curves by calculating the mean and variance, and used for recognition.
- CHANGE the viewing angle to (45-view) of the person.
- Use (Support Vector Machine (SVM)) as a classifier in classification phase.
- Do the experiment using the same gait database (CASIA-database-A)
- Calculate EER.
- Doing the implementation in MATLAB.
- Compare and discuss the results with the results of above paper.
Project 2: "Off-Line Signature Verification and Recognition"
- Applying the two approaches for Features Extraction :
- Scale Invariant Feature Transform (SIFT) approach.
- Mahalanobis Distance approach OR Hough Transform approach (you can choose either of them).
- Do the experiment using (GPDS3000GRAY signature database)
- Use (Particle Swarm Optimization-PSO) as a classifier in classification phase.
- Calculate FAR, FRR and EER for each approach.
- Doing the implementation in MATLAB.
- Compare and discuss the results for the approaches with each other.