Feature Extraction using Gabor Wavelet Filters followed by SVM Classification for Face Detection
- Login to Download
- 1 Credits
Resource Overview
This implementation performs feature extraction using Gabor wavelet filters, then employs Support Vector Machine (SVM) classification for face detection. The code requires MATLAB 2010 or later versions for execution, utilizing MATLAB's image processing toolbox for filter implementation and SVM functions for pattern classification.
Detailed Documentation
In this implementation, we first apply Gabor wavelet filters to extract discriminative features from input images. The Gabor filter bank is typically configured with multiple orientations and scales to capture texture information at different frequencies and directions. Following feature extraction, we utilize Support Vector Machine (SVM) algorithm for classification, which involves training the classifier with labeled face/non-face datasets and implementing kernel functions for optimal hyperplane separation. To successfully execute this algorithm, MATLAB 2010 or newer version is required, as it provides necessary image processing functions for Gabor filter implementation and SVM toolbox for machine learning operations.
- Login to Download
- 1 Credits