This repositiory is a small effort to document my learning specially practical implementation of all Computer vision and image processing tasks.
- Fourier Transform
- Edge Detection algorithms
- Depth estimation and Segmentation
- Feature Detection, Descriptor and feature matching algorithms
- DoG
- SIFT (Scale Invarient Feature Transform)
- SURF
- ORB
- FAST
- BRIEF
- Brute-Force Matching
- FLANN based matching
- Detection and Recognization of Objects
- HOG (Histogram of Gradients) Descriptors
- Viola-Jones Detector (CVPR-2001)
- BoW in Computer vision
- SVM and slidding Windows
- Data Driven Object Detection and classfication architecture
- LeNet (1998) -> MNIST Dataset
- AlexNet (2012) -> ImageNet Dataset
- VGG (Visual Geometry Group) Net (2014)
- Inception V1 (GoogleNet - 2015)
- Inception V2
- Inception V3
- Residual Network (ResNet -2015)
- Segmentation
- Single and Multi-Object tracking
- SORT
- DeepSORT