- Implementation of DLT for camera calibration
- Used Zhang's method for camera calibration
- Image Mosaicing- Stitching images together using SIFT to find matches between two images and consequently estimating the homography matrix.
- Stereo Correspondences
- Implementation of the famous Grabcut algorithm for image segmentation.
- Implementation of the famous Viola-Jones algorithm for face detection.
- Designed a custom CNN using pytorch and analysed the effect of the following hyperparameters-
- With Batch Norm
- Adding new layers
- With Dropout
- Different activation functions at the end
- Different pooling strategies
- Different optimizers
- Basic Augmentation like Rotation, Translation, Color Change
- Used the fastai library to perform transfer learning and train a food-type detection model.