AI for Image and Video Processing and Computer Vision
- Created By raju2006
- Last Updated December 21st, 2023
- Overview
- Prerequisites
- Audience
- Audience
- Curriculum
Description:
Dive into the dynamic world of AI for image and video processing with our comprehensive training. Explore the rapidly evolving field of computer vision through hands-on projects. From still image processing to streaming video analysis, you'll gain practical skills in object detection, medical image analysis, and video object tracking.
Course Code/Duration:
BDT9 / 3 Days
Learning Objectives:
After this course, you will be able to:
- Install Anaconda on a personal computer
- Understand the fundamental concepts of computer vision
- Understand Neural Networks
- Use Deep Learning and Convolutional Neural Networks (CNNs)
- Understand TensorFlow and Keras
- Detect, recognize and classify faces
- Understand OpenCV
- Understand feature extraction and feature matching
- Segment, manipulate and process images such as medical scans
- Understand the fundamentals of streaming video analysis
- Understand motion estimation and object tracking in video
- Implement computer vision applications for your own problems
- Basic Python Programming
- This course is designed for Software Architects, Developers, Data Engineer, Data Analyst and Machine Learning Engineer.
- This course is designed for Software Architects, Developers, Data Engineer, Data Analyst and Machine Learning Engineer.
Course Outline:
- Course Introduction
- Overview of Artificial Intelligence and Computer Vision
- Milestone 1: Install Anaconda/OpenCV
- Introduction to neural networks
- Introducing Perceptrons
- Step Function
- Updating the weights
- The math behind neural networks
- Hidden Layers
- Activation functions
- Loss functions
- Gradient descent
- Back propagation
- Vanishing gradient problem and ReLU
- Understanding the intuition behind neural networks
- From Deep Neural Networks to Deep Learning
- Understanding unstructured data
- The architecture of deep learning
- Introducing Keras/TensorFlow
- Understanding unstructured data
- Introduction to Convolutional Neural Networks (CNN)
- Convolutional layers
- Pooling layers
- Fully connected layers
- Neural Networks in TensorFlow
- Building a CNN in TensorFlow
- Milestone 2:Using TensorFlow to implement a neural network
- Image Processing Libraries
- Numpy
- Matplotlib
- OpenCV
- Python Imaging Library (PIL)
- Scikit-image
- Image Correction and Manipulation
- Contrast and Brightness Correctio
- Color Models
- Deep Learning for Computer Vision
- Image Recognition and Classification
- Milestone 3: Face Detection and Recognition
- Introduction to OpenCV
- Color Models
- Image Thresholding, Blurring, Smoothing, Edge Detection
- Image Morphological Transformations
- Image Segmentation
- Milestone 4: Medical Image Processing
- Video Analysis
- Understanding Video
- OpenCV and Video
- Capturing Video from a Camera
- Using Video Files
- Optical Flow and Motion Estimation
- Deep Learning in Optical Flow Estimation
- Milestone 5: Using OpenCV for Visual Object Tracking
- Conclusion: Next Steps
Structured Activity/Exercises/Case Studies:
- Milestone 1:Install Anaconda
- Milestone 2:Using TensorFlow to implement a neural network
- Milestone 3:Face Detection and Recognition
- Milestone 4:Medical Image Processing
- Milestone 5:Using OpenCV for Visual Object Tracking
Training material provided:
Yes (Digital format)
The curriculum is empty
[INSERT_ELEMENTOR id="19900"]
