1 / 13

Facial Identification: Creating a dataset and implementing classifiers using SVM and ANN in Matlab

This course project delves into face identification methods using SVM and ANN, starting with dataset creation and progressing to classifier implementation in Matlab. Learn to compare kernel functions, feature numbers, and ANN learning rates. The project spans 12 weeks with a comprehensive agenda, dataset preparation, algorithm implementation, data preprocessing, and valuable lessons learned along the way. Reviewing each other's work is encouraged to enhance collaboration and understanding. Start early to maximize project success and benefit from the diverse topics covered.

manton
Download Presentation

Facial Identification: Creating a dataset and implementing classifiers using SVM and ANN in Matlab

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. An Example of Course Project Face Identification

  2. Agenda

  3. Why Face Identification? • Useful • Interesting • Creating own dataset for extra credits

  4. Data set • The Extended Yale Face Database B • 2414 images of 38 human • Own data • 100 images of 4 people

  5. Classifiers • SVM (Support Vector Machine) • LIBSVM • Self Implemented SVM Optimizer • ANN (Artificial Neural Network) • Coded in Matlab

  6. Classifier Parameters • SVM • Kennel functions • ANN • Layers and units

  7. Feature Selection • Raw pixels • Down-sampling pixels • Extracted features

  8. Compare Kernel Functions

  9. Compare Feature Numbers

  10. ANN Learn Rate

  11. Report • 10 pages

  12. Schedule 12 weeks total 3 2 2 3 2 Proposal Evaluation & Report Prepare dataset Algorithms implementation Data preprocessing

  13. Lessons Learned • Start early • Review each other’s work

More Related