Basics of Computer Vision
In this training program, you will learn how to teach computers to recognize **image and video data** using fundamental **Computer Vision** methods and algorithms. You will also gain the skills to build models, analyze visual data, and extract valuable insights. In today's world, empowered by **Machine Learning**, tools like **Midjourney, Stable Diffusion, SAM, and DALL-E** allow you to generate any image you can imagine. This training program will provide you with a **solid foundation** in **Computer Vision**, covering essential concepts, advanced techniques, and practical applications in an easy-to-understand manner. After completing the course, you will either be equipped to **launch your own startup** or gain the **technical expertise** required to work as a **Computer Vision specialist** in a company. If you aspire to **contribute to the magical world of Machine Learning**, this training will serve as the **perfect starting point** for your journey. 🚀
Training table
Information about the training
Computer Vision algorithms are widely used in agriculture for recognizing diseases from plant images, in medicine for image-based diagnostics, in space exploration, security, and surveillance, and are among the new artificial intelligence solutions that reduce costs. In a world where Artificial Intelligence and Machine Learning are rapidly expanding, one example of the use of Computer Vision algorithms is in self-driving cars, where models can issue warnings. The recognition of humans, animals, and other objects based on images by computers is widely applied in many industries and government agencies to increase efficiency and help prevent fraud. In the Computer Vision fundamentals training program, you will learn through real projects how to perform operations on images, transformations, modeling with Convolutional Neural Networks, overfitting and generalization, measuring model performance, optimizers and loss functions, data augmentation, early stopping, batch normalization, and building the latest models with transfer learning. Through Python, you will gain the skills to apply Computer Vision algorithms using libraries such as OpenCV, numpy, Pytorch, Keras, and TensorFlow. During the training, you will work on practical computer vision solutions such as diagnosing pneumonia from X-ray images, detecting diseases in plants, and creating algorithms for recognizing car license plates.
Who is this training for?
Students
Programmers
Data Science Experts
Artificial Intelligence Enthusiasts
Researchers and Academics
Certificate
It provides a certificate to those who complete the training as Certified Data Scientist and others. You can see a sample certificate on the right.
Basics of Computer Vision
Computer Vision Explained in 5 Minutes
AI Sciences
In this video, we are going to fully explain what computer vision is.
Syllabus
Session 1
Introduction to Computer Vision
Applications of Computer Vision
Recent Research in Computer Vision
Introduction to OpenCV
Converting Images to Grayscale
Color Shades and Channels – RGB and HSV
Case Study 1
License Plate Recognition
Session 2
Operations on Images in OpenCV
Drawing Shapes on Images
Transformations - Translations and Rotations
Resizing, Scaling, Interpolation, and Cropping
Arithmetic and Bitwise Operations
Repetitions, Blurring, and Sharpening Operations on Images
Thresholding, Binarization & Adaptive Thresholding
Dilation, Erosion, and Edge Detection
Case Study 2
Face Recognition and Image Augmentation for Identifying Bad Habits in Children with Autism
Session 3
Modeling in PyTorch and Keras
Transformation Pipeline
Exploring and Visualizing Data
Data Loaders
Building Models (PyTorch / Keras / TensorFlow)
Optimizers and Loss Functions
Training the Model
Saving the Model and Displaying Results
Visualizing Results
Case Study 3
Building a Model for Defect Detection in Text
Session 4
Measuring Model Performance
Comparing PyTorch and Keras Libraries
Model Performance Evaluation
Confusion Matrix and Classification Report
Displaying Misclassified Results in Keras and PyTorch
Overfitting, Generalization
Dropout, L1 and L2 Regularization
Case Study 4
Building a Fire Detection Algorithm
Session 5
Model Tuning and Performance Enhancement
Data Augmentation
Early Stopping
Batch Normalization
When to Use Regularization
Regularized and Non-Regularized Model Building on FNIST Dataset in Keras and PyTorch
Case Study 5
Pneumonia Detection from Chest X-Rays
Session 6
Transfer Learning Algorithms
History and Evolution of Convolutional Neural Networks
LeNet, AlexNet
VGG16 and VGG19
ResNets, MobileNetV1 and V2
InceptionV3, SqueezeNet, EfficientNet
DenseNet and The ImageNet Dataset
Case Study 6
Model for Detecting Plant Diseases
Trainers
Emil Mirzəyev
SÜNİ İNTELLEKT VƏ STRATEJİ QƏRARQƏBULETMƏ RESEARCHER, UNİVERSİTY COLLEGE LONDONDr. Emil Mirzayev holds a dual PhD in Economics and Business Administration and is currently engaged in scientific research at the intersection of Artificial Intelligence and Strategic Decision-Making at University College London, one of the world's top universities. He has nearly 10 years of experience with Python and Data Science, and has presented his work at prestigious institutions like MIT, Harvard, and LBS, as well as at numerous international conferences. In Azerbaijan, he has also conducted multiple free workshops on topics related to Machine Learning and AI.
Əhməd Əhmədov
Senior Data Scientist, Porsche AGAhmad Ahmadov pursued his master’s education in "Data Mining" and "Big Data" at Yonsei University in South Korea. He has more than 10 years of experience in artificial intelligence and data analytics. He has been working at Porsche AG in Germany for 6 years as a Senior Data Scientist and Tech Lead. He is mainly responsible for the development of AI models and project management in fields such as "GenAI," "Digital Assistants," "Customer Mobility Predictions," "Charging Experience Optimization," and "Content Quality Analysis."
His previous professional experiences include:
* Dresden University (Germany): Scientific Researcher in AI and Data Science. Research areas: "Data Imputation," "Data Quality," "Information Retrieval," "Web Tables," "Semi-Structured Datasets," and "Machine Learning." (4 years)
* Bakcell: ERP Technical Analyst. (1 year)
Additionally, he is the author of numerous scientific articles published at various international conferences.