Overview
Computer vision is a rapidly growing field in which machines are able to interpret and process visual information. This field has been enabled by advances in machine learning, deep learning, and image processing.
Computer vision is used to build systems that are able to recognize objects, identify patterns and make decisions based on the visual data. It is used for applications such as autonomous vehicles, facial recognition, robotics, medical imaging and more.
Tools Covered
- Anyone who has an interest in Deep Learning, Computer Vision and its applications and is looking forward to further explore these domains to either extend their skillset for career opportunities or to simply learn about Computer Vision Systems.
- Familiarity with AI Tools and Technologies: Participants will be exposed to various AI tools and technologies, such as TensorFlow, Jupyter and OpenCV, and will learn how to use them to develop AI models and applications.
- Hands-on Experience with AI Projects: Participants will engage in practical exercises and real-world projects, allowing them to apply their learning to build AI models, train them with data, and evaluate their performance. This will help them gain practical experience in developing AI applications.
- Computer Vision: Participants will learn the basics of computer vision, including image processing, object detection, image segmentation, and facial recognition. They will also learn how to build computer vision applications using AI techniques, such as convolutional neural networks (CNNs).
Course Outline
- Week 1
- Week 2
- Python Basics
- Open CV
- Image Matrix
- Resolution of Image
- Different Video Streaming Protocols
- Threshold, Multiplication
- What is Video
- Read Image
- Gradients
- Frames Per Second
- Week 3
- Week 4
- Neural Network – Single Node
- Optimizers
- Multilayer Perceptrons
- Evaluation Metrics, Hyperparameter Tuning
- Forward Propagation\ Backward Propagation\
- Image Classification Project – live demonstration
- CNN Introduction + Background + Applications
- Making a CNN in Python with Tensorflow
- Different layers (Each layer explained in depth)
- Image Classification Project – live demonstration
- Parameters/ Hyperparameters + Optimizers + Side concepts
- CNN Variants
- Week 5
- Week 6
- Transfer learning
- Inception v1, v2, v3
- VGG network
- Autoencoders
- RESNET network
- Section introduction
- Section introduction
- Problem of scale and shape
- RCNN model family and its limitiations
- Object localization
- Retina net
- Yolo
- Object detection
- IOU and non-max suppression
- RCNN model family and its limitations
- Yolo
- Project : Custom object detector
- Week 7
- Week 8
- Simple face recognition 1: Faces in wild (use PCA, SVM
- MTCNN
- Simple face recognition 2: using DLIB and KNN/SVM
- Project: Custom Face Detection and Recognition
- FaceNet by Google
- Introduction and Applications
- PIX2PIX and Cycle GAN
- Generator and Discriminator
- Project 2: Satelite image to Google map like image translation
- Project 1: create MNIST like dataset
Our Methodology
Industry Usecases
With real world projects and immersive content built in partnership with top tier companies, you’ll master the tech skills companies want.
Technical Support
Our knowledgeable mentors guide your learning and are focused on answering your questions, motivating you and keeping you on track.
Career Mentorship
You’ll have access to resume support, portfolio review and optimization to help you advance your career and land a high-paying role.
Frequently Asked Questions
Since our trainings are led by Industry Experts so it is made sure that content covered in workshop is designed with hand on knowledge of more than 70-75 % along with supporting theory.
Yes, You will be awarded a course completion certificate by Dice Analytics if you pass the course.
For this professional workshop, you need to have a PC with minimum 4GB RAM and ideally 8GB RAM.
Don’t worry! We have got you covered. You shall be shared recorded lectures after each session, in case you want to revise your concepts or miss the lecture due to some personal or professional commitments.
Yes, you can rejoin the training within the span of an year of your registration. Please note following conditions in case you’re rejoining.
1) There are only 5 seats specified for rejoiners in each iteration.
2) These seats will be served on first come first basis.
3) If you have not submitted your complete fee, you may not be able to rejoin. Your registration would be canceled