Machine Learning for Computer Vision

Brochure

Apply Online

● Introduction to Image Processing and Computer Vision (CV), Main Goals and challenges of the CV, Image Processing Goals and Tasks. 

● Traditional approaches in Image Processing, Feature Extraction and their applications to Image Processing: Natural Image Classification, Image Enhancement, edge Detection, Segmentation. Image denoising

● Introduction to Artificial Intelligence (AI) and Machine Learning (ML) AI and ML, Supervised and Unsupervised Learning, Traditional ML approaches,

● Neural Network as a learning machine, forward and backward propagation, Applications in computer vision. Image classification.

● Training Neural Networks, optimization, regularization,

● Introduction to Deep Learning (DL) Basic differences between Conventional ML and DL approaches, Challenges in training deep neural networks, Vanishing /exploding gradient problems

● Introduction to Convolutional Neural Network , The Convolution Operation, Basic architecture of a Convolution Neural Network, Pooling and Batch Normalization layers,

● CNNs as feature extractors, Image classification using CNN,

● State of the Art Deep CNN Architectures, CNN for Image Enhancement and Segmentation.

● Autoencoder for Feature Extraction and Image Enhancement Applications of CNN in agriculture, Medical image analysis and Satellite Imagery

● Recent Trends in ML for CV