Programme Parameters
Graduate / Intermediate
4 Weeks (40 Hrs)
Online (e-LMS)
• A basic understanding of the subject area and fundamental programming or scientific concepts.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
Computer Vision and Image Processing bridges two eras: the classical toolkit and modern deep learning. You start with how images are represented and manipulated — filtering, edges, morphological operations and feature detection — then build up to convolutional neural networks for image classification. From there you tackle the tasks that power real applications: object detection, semantic segmentation and transfer learning from pretrained backbones. Every topic is grounded in hands-on work with real images, so you leave able to take a visual problem and build a model that solves it. A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
This course covers computer vision from classical image processing to deep learning — filtering, feature detection, CNNs, object detection and segmentation — on real images.
📋 Course Objectives
1. Represent and manipulate images with classical processing.
2. Detect edges, features and regions of interest.
3. Build CNNs for image classification.
4. Apply object detection and semantic segmentation.
5. Use transfer learning from pretrained vision models.
👥 Who Should Enroll?
• Developers and data scientists entering computer vision
• Engineers building vision into products
• Researchers working with image data
• Students specialising in visual computing
🚀 Key Learning Outcomes
• The ability to build a computer-vision model end to end.
• A working image-classification or detection project.
• Fluency across classical and deep vision methods.
• A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
💎 What You'll Gain
Live & Recorded Sessions
Lifetime access to class recordingse-Certificate on Completion
Cryptographically verified credentialPost-Programme Support
Direct access to mentors & councilHands-On Experience
Notebooks, real-world code & datasetsCurriculum Outline
Visual Computing Fundamentals and Computer Vision Foundations
Develop a comprehensive understanding of visual computing concepts, including image formation and representation • Analyze the fundamental principles of computer vision, including image processing, feature extraction, and object recognition • Configure visual computing environments using Python and OpenCV to implement basic image processing techniques
Image Processing, Augmentation, and Feature Extraction
Implement image filtering and enhancement techniques using spatial and frequency domain methods • Design and evaluate image augmentation strategies to improve model robustness and generalization • Extract and analyze visual features from images using techniques such as edge detection, thresholding, and feature descriptors
CNN Architectures, Transfer Learning, and Computer Vision Models
Design and implement convolutional neural network (CNN) architectures for image classification and object detection tasks • Evaluate the performance of pre-trained CNN models using transfer learning and fine-tuning techniques • Develop and train custom CNN models using TensorFlow and Keras to solve computer vision problems
Object Detection, Segmentation, and Localization
Implement object detection algorithms such as YOLO, SSD, and Faster R-CNN using deep learning frameworks • Analyze and evaluate the performance of semantic segmentation models using metrics such as IoU and accuracy • Develop and train models for instance segmentation and object localization using techniques such as Mask R-CNN and RetinaNet
Video Analysis, Temporal Models, and Real-Time Processing
Develop and implement video analysis pipelines using techniques such as object tracking and motion estimation • Design and evaluate temporal models for video classification and action recognition tasks • Configure and optimize real-time video processing systems using GPU acceleration and parallel processing techniques
Model Optimization, Quantization, and Edge Deployment
Optimize and prune deep learning models for computer vision tasks using techniques such as knowledge distillation and quantization • Evaluate the performance of optimized models on edge devices such as Raspberry Pi and NVIDIA Jetson • Deploy and test computer vision models on edge devices using frameworks such as TensorFlow Lite and OpenVINO
Industry Applications and Computer Vision Use Cases
Analyze and evaluate the applications of computer vision in industries such as healthcare, finance, and retail • Develop and implement computer vision solutions for real-world problems such as image classification, object detection, and segmentation • Design and propose computer vision systems for emerging applications such as autonomous vehicles and smart cities
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | OpenCV |
| Covered Tool / Platform | TensorFlow |
| Covered Tool / Platform | Keras |
| Covered Tool / Platform | NumPy |
| Covered Tool / Platform | SciPy |
Frequently Asked Questions
Scholar Feedback & Reviews
Based on 0 scholar submissions
Rating Breakdown
No verified reviews published yet. Be the first to share your academic experience.
Leave Scholar Feedback
Your rating will help prospective scholars. Ratings below 3 stars are routed privately to the faculty mentor for immediate response.
