Enroll
@ 35% Discount
Learn
Pass with Honours!
Earn
$100 per Course
Leaderboard
Read More
OpenCV 100-day AI coding challenge was a great course that covered basics to advanced topics in AI/ ML and all the foundation work to build one’s knowledge. Previously, being self-taught I had to scramble various sites and videos but, with OpenCV’s course, everything I needed was right in front. Assistant instructors were able to answer all questions within a day. The exercises range from basic to advanced. Libraries and concepts of Pytorch and Tensorflow are also covered. I had a great time working on all the classes, tough but rewarding. I hope to continue my learning and land a position as an associate programmer and further my skills in data analysis.
Read More
I've always been fascinated by game-changing technology and how it helps my clients succeed.
For deep learning/AI, I had spent some money on a few courses but was barely satisfied until I found the #CVDLMasterProgram offered by #OpencvUniversity. The project is more comprehensive and challenging than the other courses that I've paid for.
In the past 3 months, I have completed 2 out of 6 courses with excellent scores, which have greatly challenged my existing knowledge and skills in breadth and depth. I am yet holding the first place in one of the challenges on Kaggle.
Next, I am going to review the past courses and the codes to make sure I know every single detail well already, then learn PyTorch and use C++ to process computer vision and images. I am excited that the program provides well-rounded courses so that I can learn them all in one program. I couldn’t agree more with what Dr. Satya Mallick says in the introduction video: “Eventually, you need to learn them all.”
Another greatly valuable part of the program is that the instructors are very prompt in answering questions. Whether my questions were about minor details or merely related questions like cloud platform settings, the instructors gave clear and precise answers, which I've never experienced with courses I've paid for in the past.
This program is bringing me closer to the core areas of AI. Many thanks to #OpencvUniversity!
For deep learning/AI, I had spent some money on a few courses but was barely satisfied until I found the #CVDLMasterProgram offered by #OpencvUniversity. The project is more comprehensive and challenging than the other courses that I've paid for.
In the past 3 months, I have completed 2 out of 6 courses with excellent scores, which have greatly challenged my existing knowledge and skills in breadth and depth. I am yet holding the first place in one of the challenges on Kaggle.
Next, I am going to review the past courses and the codes to make sure I know every single detail well already, then learn PyTorch and use C++ to process computer vision and images. I am excited that the program provides well-rounded courses so that I can learn them all in one program. I couldn’t agree more with what Dr. Satya Mallick says in the introduction video: “Eventually, you need to learn them all.”
Another greatly valuable part of the program is that the instructors are very prompt in answering questions. Whether my questions were about minor details or merely related questions like cloud platform settings, the instructors gave clear and precise answers, which I've never experienced with courses I've paid for in the past.
This program is bringing me closer to the core areas of AI. Many thanks to #OpencvUniversity!
Read More
🎓 Excited to announce that I've completed the Mastering OpenCV with Python course at OpenCV University with an impressive 89% grade! 💻 #100daysAIchallenge
I can't wait to apply my newly acquired knowledge and skills to tackle real-world challenges in the field of computer vision. Let's continue pushing the boundaries of what's possible together! 💡 #OpenCV #ComputerVision #Gratitude #LearningJourney
A heartfelt thank you to my mentors Sajin Sam Abraham and Anjana Agarwal for their guidance, support, and invaluable insights throughout this journey.
I can't wait to apply my newly acquired knowledge and skills to tackle real-world challenges in the field of computer vision. Let's continue pushing the boundaries of what's possible together! 💡 #OpenCV #ComputerVision #Gratitude #LearningJourney
A heartfelt thank you to my mentors Sajin Sam Abraham and Anjana Agarwal for their guidance, support, and invaluable insights throughout this journey.
Read More
I am thrilled to share my experience completing the OpenCV course and 100-day AI challenge.🎉
The course provided comprehensive insights into computer vision, and the well-structured modules made learning enjoyable. The quizzes were particularly valuable.
The detailed explanations and clear demonstrations enhanced my understanding, enabling me to achieve an outstanding result. I appreciate the course's relevance in real-world scenarios, and I now feel confident in applying OpenCV techniques to various projects.
Kudos to the instructors for their expertise and the course design, which played a pivotal role in my success! 👏
#opencv #computervision #opensource #certificate #opencvuniversity #imageprocessing #objectdetection #pythonprogramming #python Satya Mallick
The course provided comprehensive insights into computer vision, and the well-structured modules made learning enjoyable. The quizzes were particularly valuable.
The detailed explanations and clear demonstrations enhanced my understanding, enabling me to achieve an outstanding result. I appreciate the course's relevance in real-world scenarios, and I now feel confident in applying OpenCV techniques to various projects.
Kudos to the instructors for their expertise and the course design, which played a pivotal role in my success! 👏
#opencv #computervision #opensource #certificate #opencvuniversity #imageprocessing #objectdetection #pythonprogramming #python Satya Mallick
Previous
Next
Courses Offered
Play Video
DLPT
Start solving Computer Vision problems using Deep Learning techniques and the PyTorch framework. Dive into the architecture of Neural Networks, and learn how to train and deploy them on the cloud.
Available in Python
|
$799
Play Video
GENAI
Dive deep into Stable Diffusion. Learn all the techniques of generating images, fine-tuning Stable Diffusion on your own images and even training a GPT language model.
Available in Python
|
$159
Play Video
DLAP
Build systems and applications using advanced Computer Vision and Deep Learning techniques, and understand deployment using cloud-based services.
Available in Python
|
$499
Play Video
CVIP
Build a solid understanding of OpenCV tools used for Image Processing, Computer Vision, and Video Processing, and lay a strong foundation for solving Computer Vision problems.
Available in Python & C++
|
$499
Play Video
MOCV
Start your AI journey by learning the fundamentals of Image Processing and Computer Vision through 21 modules, video instructions, code explanations, and example applications.
Available in Python
|
$149
Play Video
DLTK
Gain in-depth knowledge about Neural Networks, prepare datasets and study DeepNet architectures used for solving various Computer Vision problems.
Available in Python
|
$799
Play Video
CVIP
Build a solid understanding of OpenCV tools used for Image Processing, Computer Vision, and Video Processing, and lay a strong foundation for solving Computer Vision problems.
Available in Python & C++
|
$499
Play Video
MOCV
Start your AI journey by learning the fundamentals of Image Processing and Computer Vision through 21 modules, video instructions, code explanations, and example applications.
Available in Python
|
$149
Play Video
DLAP
Build systems and applications using advanced Computer Vision and Deep Learning techniques, and understand deployment using cloud-based services.
Available in Python
|
$499
Play Video
DLTK
Gain in-depth knowledge about Neural Networks, prepare datasets and study DeepNet architectures used for solving various Computer Vision problems.
Available in Python
|
$799
Play Video
DLPT
Start solving Computer Vision problems using Deep Learning techniques and the PyTorch framework. Dive into the architecture of Neural Networks, and learn how to train and deploy them on the cloud.
Available in Python
|
$799
Play Video
GENAI
Dive deep into Stable Diffusion. Learn all the techniques of generating images, fine-tuning Stable Diffusion on your own images and even training a GPT language model.
Available in Python
|
$159
A glimpse of the topics covered
What's covered in this course?
Course Topics
- Basics of Image Formation and Image Formats
- Reading, Display and Writing Images in OpenCV
- Resizing, cropping, annotating, creating a Region of Interest
- Image thresholding, Bitwise operations and Masking
- Creating Digital signatures using Alpha Blending
- Color space conversion and different Color Spaces
- Image Histograms and enhancement using Histogram Equalization
- Deforestation analysis using Color Segmentation
- Satellite Imagery analysis using GeoTIFF Images
- Reading and Writing videos using OpenCV
- Motion Detection using Background Subtraction
- Build an Intruder Detection System
- Reading and Writing videos using OpenCV
- Motion Detection analysis using Background Subtraction
- Build an Intruder Detection System
- Image Filtering using Convolution Operations
- Edge Detection using Sobel Filters and Canny algorithm
- Artistic Renderings using Image Filters
- Noise Reduction using Median and Bilateral Filters
- Image Inpainting for Image Restoration
- Building a streamlit application on image restoration using Inpainting.
- Overview of ArUco markers
- Application: AR using ArUco Markers
- Introduction to OpenCV’s DNN Module.
- Image Classification using OpenCV DNN Module
- Super-Resolution on Images
- Face Detection using DNN Module
- Facial Landmarks Detection
- Building a Real-time Blink Detection application
- Object Detection using MobileNet SSD, YOLOv4 and YOLOv5
- Building a Social Distance Monitoring Application
- Introduction to Object Tracking Models in OpenCV
- Human Pose Estimation using MediaPipe
- Sports Analytics using MediaPipe
- Human Segmentation using Mediapipe
- Text Detection using EAST and Differentiable Binarization (DB)
- OCR on Natural Images
- Language Translation using OCR
- Building webapps using Streamlit
- Deploying webapps on AWS, GCP, Azure
A glimpse of the topics covered
What's covered in this course?
Course Topics
- Introduction to Computer Vision
- Introduction to Digital Images
- Basic Image operations
- Mathematical operations on images
- Video Read-Write using HighGUI
- Using KeyBoard and Mouse as Inputs
- Using Trackbars
- Annotating Images with Text and Boxes
- Image Thresholding
- Morphological Operations like Erosion & Dilation
- Contour Analysis
- Blob Detection
- Color Spaces and Transforms
- Histogram Equalization
- Image filtering & Convolution
- Image Smoothing & Edge Detection
- Hough Transforms for Line and Circle Detection
- High Dynamic Range Imaging
- Seamless Cloning
- Image Inpainting
- Affine Transforms & Homography
- Feature matching using RANSAC
- Finding Objects using Feature Matching
- Application: Image Alignment and Creating Panoramas
- Image Segmentation using GrabCut
- Image Classification using HoG and SVM
- Object Detection using Haar Cascades
- Pedestrian Detection
- Motion Sstimation using Optical Flow
- Video Stabilization
- Object Tracking
- Multi Object Tracking in OpenCV
- Image Classification using Caffe and TensorFlow
- Object Detection with SSD and YOLO
- Face Detection using SSD
- Human Pose Sstimation using OpenPose
- Selfie Application with Instagram Filters
- Object Detection & Tracking Integration
- Document Scanner using Homography
- Implementing Chroma Keying
A glimpse of the topics covered
What's covered in this course?
Course Topics
- Introduction to Artificial Intelligence
- NumPy Refresher
- Introduction to PyTorch
- What is inside an ML algorithm?
- Understanding Neural Networks
- Building Neural Networks in PyTorch
- Building Blocks of a Neural Network
- Multi-Class Classification using PyTorch
- Image Classification
- Convolutional Neural Networks
- LeNet in PyTorch
- Evaluation Metrics for Classification
- Important CNN Architectures
- Optimizers and LR Schedulers
- Training Deep Networks
- Using your own Data
- Model Complexity, Generalization and Handling Overfitting
- Gaining Insights
- Troubleshooting Training with TensorBoard
- Transfer Learning and Fine-Tuning in PyTorch
- Write your own Custom Dataset Class
- PyTorch Lightning
- Introduction to Semantic Segmentation
- PyTorch Segmentation Models and Custom Dataset
- Transposed Convolutions
- Fully Convolutional Networks
- UNet
- Dilated Convolution
- DeepLabV3
- Instance Segmentation
- Introduction to Object Detection
- Hands on with Object Detection
- Classification to Detection
- Non Maximum Supression
- Evaluation Metrics
- Popular Object Detection Architecture
- Understanding Faster RCNN
- Detectron 2
- Ultralytics YOLO
- Create a Custom Object Detector
A glimpse of the topics covered
What's covered in this course?
Course Topics
- Introduction to Artificial Intelligence
- NumPy refresher
- Introduction to TensorFlow and Keras
- What is inside an ML algorithm?
- Neural Network Building Blocks
- Loss Functions for Classification and Regression
- Understanding the Keras Sequential and Functional APIs
- Image Classification using Multilayer Perceptron
- Convolution operation
- CNN building blocks and Layers
- Implement CNNs using TensorFlow Keras
- Evaluation of Classification Performance
- Advanced Optimizers in Keras
- Learning Rate Decay methods
- Training Deep Neural Networks
- Regularization methods in Deep Learning
- Troubleshooting training with TensorBoard
- Leverage pre-trained models
- Handling Data in TensorFlow using TF Data, Sequence Class, and TF Records
- Introduction to Object Detection
- Object Detection Building Blocks
- Evaluation metrics in Object Detection like mAP
- Two-Stage Object Detectors like Faster RCNN
- You Only Look Once (YOLO)
- Single Stage Multibox Detector (SSD)
- EfficientDet and RetinaNet
- How to write a custom Object Detector from scratch?
- Using the TensorFlow Object Detection (TFOD) API
- Fine-tuning of Object Detection Models available on TFOD API on a subset of Pascal VOC data.
- Building a Custom SSD Model with FPN and training it on PenFudanPed Dataset
- Semantic Segmentation Building Blocks
- Dilated Convolution and Transposed Convolution
- Semantic and Instance Segmentation
- Evaluation metrics for Semantic Segmentation
- Fully Convolutional Network (FCN)
- U-Net
- DeepLab
- Mask-RCNN
- Real-time Posture analysis using MediaPipe Pose
- Drowsy Driver Detection using MediaPipe
- Introduction to GANs
- Vanilla GAN using Fashion MNIST
- DCGAN using Flickr Faces
- CGAN using Fashion MNIST
A glimpse of the topics covered
What's covered in this course?
Course Topics
- Different face processing applications
- Facial Landmark Detection
- Application: Face Alignment
- Train a custom Facial Landmark Detector
- Face Averaging
- Face Morphing
- Application: Smile Detection
- Head Pose Estimation
- Face Swapping
- Application: Beard Filter
- Application: Aging Filter
- Non-linear Deformations for creating Filters
- Introduction to Face Recognition
- Eigen & Fisher Faces, Local Binary Patterns Histograms
- Face Recognition API in OpenCV
- Deep Learning-based Face Recognition
- Basics of Neural Networks
- The Keras Framework [Will be updated to PyTorch]
- Convolutional Neural Network for Image Classification
- Transfer Learning and Fine-tuning and Logging
- Object Detection overview
- YOLO Models for Object Detection [Will be updated to YOLOv8]
- YOLO-NAS [Will be added]
- RT-DETR [Will be added]
- The OCR Pipeline
- Graphic Text OCR using Tesseract
- Text Detection with EAST & CRAFT
- Automatic Number Plate Recognition
- OCR using Transformer OCR (TrOCR) [Will be added]
- Create a web application using Flask
- Deploy a web application on Heroku
- Deploy a web application on Google GCP
Testimonials
Embarking on the 'Deep Learning with TensorFlow and Keras' course was a transformative experience that surpassed my expectations. The course content upholds exceptional quality standards, delivered with remarkable clarity. It seamlessly integrates theoretical insights, practical examples, and hands-on code implementation, providing an enriching learning experience. The meticulously structured curriculum, coupled with a series of challenging assignments and projects ranging from fundamental to advanced levels, significantly contributed to solidifying my understanding of the subject matter. What stood out for me was the timely assistance available when tackling assignments and projects. The support I received was instrumental in overcoming hurdles and completing the course successfully. I wholeheartedly endorse this course to individuals with a sincere interest in acquiring in-depth knowledge of Deep Learning, Machine Learning, and Artificial Intelligence.
I want to express my gratitude to openCV for the excellent courses I have had the pleasure of taking. The quality of the content, the clarity of the explanations given by Dr. Satya Mallick, the fully functional sample codes and the quick and concrete technical advice have exceeded my expectations. The learning gained not only gave me solid skills in computer vision, but also the confidence to apply them in real projects for public safety. For this reason, I highly recommend this educational experience to anyone looking to learn or specialize in the field of artificial vision. Thank you openCV for giving more than what you offer and contributing a lot to achieve a better world!
I wanted to express my sincere gratitude for the incredible learning experience the « Mastering OpenCV using Python » course provided. As a engineering student in my M2 year, participating in the course during the 100 AI Days Challenge was truly enlightening.
The structured content progression from image formation to advanced computer vision techniques during the 100 AI Days Challenge was invaluable.
Moreover, the management team's responsive and reactive support contributed to a positive learning environment. Thank you for a professionally curated course and an outstanding experience.
Thank you for this valuable opportunity to enhance my skills in computer vision and Python programming. I look forward to applying this knowledge in my future endeavors.
The 'Deep Learning with TensorFlow & Keras' course from OpenCV was a fantastic experience. Before the course, I had some theoretical knowledge but struggled to put it into practice. This course changed that! The combination of clear explanations, hands-on coding examples, and well-designed projects helped me solidify my understanding and build real-world deep learning solutions. Highly recommended!
Have questions
about the challenge?
Certificates
You will receive a Certificate of Excellence if you score more than 70% marks on the graded quizzes + assignments + projects within 6 months of enrolling in the course.
Honor Certificate
Certificate of Excellence
Frequently Asked Questions
You have lifetime access to the course material. You can complete the courses at your pace. If you complete any course within 100 Days, you will receive a $100 reward for each course you complete.
The reward will be pure cash transferred to your original mode of payment.
Yes, you can start all courses and complete them simultaneously. There is not restriction.
Yes, you may get a chance for a paid internship with us.
No, the Mastering Generative AI for Art course is excluded from the 100-Day AI Challenge.
Refund Policy
For all refund requests and queries, please write to us at [email protected].
Courses
You will have a window of 30 days after you start the course to request a full refund.
Programs
You will have a window of 30 days after you start the first course in the program to request a full refund. Refunds are offered for the entire program and not for individual courses within the program.
Ready to begin your learning journey with OpenCV University?