Model Curriculum
PYTHON WITH COMPUTER VISION
SECTOR: IT & ITeS
SUB-SECTOR: Data Science & AI
OCCUPATION: Computer Vision Engineer
REF ID: IT/CV/Q001
NSQF LEVEL: 5
1
Python with Computer Vision
CURRICULUM / SYLLABUS
This program is aimed at training candidates for the job of a "Computer Vision Engineer" in
the "IT & ITeS" sector/industry and aims to build the following key competencies:
Program Name Python with Computer Vision
Qualification Pack Name & IT/CV/Q001, v1.0
Reference ID
Version No. 1.0 Version Update Date NA
Pre-requisites to Training Basic knowledge of Python and machine learning.
Preferably a graduate or diploma in Computer Science/IT.
Training Outcomes After completing this program, participants will be able to:
Understand computer vision fundamentals: Learn
image processing and feature extraction techniques.
Build computer vision models: Implement and train
models using libraries like OpenCV and TensorFlow.
Apply deep learning to computer vision tasks: Use
CNNs for image classification and object detection.
Deploy computer vision models: Integrate computer
vision applications into real-world systems.
Course Structure
This course encompasses 4 National Occupational Standards (NOS) of "Computer Vision
Engineer" Qualification Pack issued by the IT Skill Council.
Sr. Module Key Learning Outcomes Equipment
No. Required
1 Introduction to Python programming basics: Refer to Unique
Python and Variables, loops, functions equipment
Computer Vision Overview of computer vision and its Required section
applications (e.g., image
Theory Duration
(hh:mm) classification, object detection)
10:00 Introduction to OpenCV and Python
libraries for image processing
Practical Duration Setting up Python environment
(hh:mm) (installing OpenCV, NumPy,
10:00 Matplotlib)
Basic image loading, displaying, and
2
saving with OpenCV
Simple image manipulation
(cropping, resizing)
2 Image Processing Image formats and color spaces Refer to Unique
with OpenCV (RGB, Grayscale, HSV) equipment
Feature detection: Edges, corners, Required section
Theory Duration
and contours
(hh:mm)
10:00 Image transformations: Scaling,
rotation, and flipping
Practical Duration Applying filters: Gaussian blur, edge
(hh:mm) detection (Canny), thresholding
15:00 Detecting contours and drawing
bounding boxes on images
Hands-on project: Object detection
using contours (e.g., detecting
shapes in images
3 Advanced Image Morphological operations: Dilation, Refer to Unique
Processing erosion, opening, and closing equipment
Image segmentation basics Required section
Theory Duration Introduction to histograms and
(hh:mm) histogram equalization
10:00 Implementing morphological
transformations on images
Practical Duration Image segmentation using color
(hh:mm) thresholding
15:00 Histogram equalization for image
enhancement
4 Introduction to Introduction to deep learning and Refer to Unique
Convolution Neural neural networks equipment
Networks (CNNs) Basics of CNN architecture: Required section
Convolutional layers, pooling layers,
Theory Duration fully connected layers
(hh:mm) Overview of image classification
10:00 tasks
Building a simple CNN using
Practical Duration TensorFlow/Keras
(hh:mm) Training a CNN on the MNIST dataset
15:00 for digit classification
Evaluating the model using accuracy,
3
precision, and recall
5 Image Classification Understanding overfitting and Refer to Unique
using CNNs regularization techniques (dropout, equipment
data augmentation) Required section
Theory Duration Advanced CNN architectures: VGG,
(hh:mm) ResNet
10:00 Transfer learning with pre-trained
models
Practical Duration Implementing data augmentation
(hh:mm) techniques (e.g., flipping, rotation)
15:00 Fine-tuning pre-trained models for
custom image classification tasks
Hands-on project: Training a CNN on
CIFAR-10 or a custom dataset
6 Object Detection Introduction to object detection Refer to Unique
Technique algorithms: YOLO, Faster R-CNN equipment
Region proposal networks (RPN) and Required section
Theory Duration sliding window techniques
(hh:mm) Applications of object detection in
10:00 autonomous systems
Implementing YOLO for real-time
Practical Duration object detection
(hh:mm) Working with pre-trained object
15:00 detection models (TensorFlow
Object Detection API)
Hands-on project: Detecting objects
in real-world video feeds (e.g.,
pedestrians, vehicles)
7 AI Integration Introduction to image segmentation: Refer to Unique
Semantic vs. instance segmentation equipment
Theory Duration Segmentation models: U-Net, Mask Required section
(hh:mm) R-CNN
10:00 Applications of segmentation in
medical imaging and self-driving cars
Practical Duration Implementing U-Net for image
(hh:mm) segmentation
15:00 Using Mask R-CNN for instance
segmentation on COCO dataset
Hands-on project: Segmenting
objects in images (e.g., people,
animals)
8 Model Deployment Model deployment basics: Exporting Refer to Unique
4
and AI Integration models for inference equipment
Serving models via REST APIs using Required section
Theory Duration Flask/FastAPI
(hh:mm) Introduction to cloud deployment
10:00 (AWS, GCP)
Deploying a computer vision model
Practical Duration with Flask and serving it as a web API
(hh:mm) Using cloud services to deploy and
15:00 scale a computer vision model
Hands-on project: Building a real-
time computer vision application and
deploying it on the cloud
9 Capstone Project End-to-end computer vision project: Refer to Unique
Choose a topic such as image equipment
Practical Duration classification, object detection, or Required section
(hh:mm) image segmentation
30:00 Steps: Data collection,
preprocessing, model building,
evaluation, and deployment
Presentation of the final project
Total Duration: Unique Equipment Required:
Theory Duration Laptop with at least 8 GB RAM
(hh:mm) Projector
130:00 Python IDE (Jupyter Notebook, PyCharm)
OpenCV, TensorFlow, and Keras libraries installed
Practical Duration Access to image datasets for computer vision projects
(hh:mm) Internet connection for cloud-based deployment
170:00
Grand Total Course Duration: 300 Hours
Technical Outcome of Course:
Overview of computer vision concepts
5
Tools: OpenCV, Python libraries for image processing | Laptop, Projector, Python IDE
| 20:00 | 20:00 | IT/CV/N0801 | | 2 | Image Processing with OpenCV | - Image
reading, writing, and manipulation
Feature detection: edges, corners, and contours
Image transformations: scaling, rotation, and filtering | Laptop, Projector, Python
IDE, OpenCV | 25:00 | 35:00 | IT/CV/N0802 | | 3 | Convolutional Neural Networks
(CNNs) | - Introduction to CNNs for image classification
Building CNNs with TensorFlow and Keras
Image datasets: MNIST, CIFAR-10, ImageNet | Laptop, Projector, Python IDE | 30:00
| 40:00 | IT/CV/N0803 | | 4 | Object Detection and Segmentation | - Object
detection techniques: YOLO, Faster R-CNN
Image segmentation techniques: U-Net, Mask R-CNN
Practical applications in autonomous systems | Laptop, Projector, Python IDE,
Datasets | 30:00 | 40:00 | IT/CV/N0804 | | 5 | Model Deployment and AI
Integration | - Exporting and deploying computer vision models
Integrating models into applications using Flask/REST API
Cloud deployment and scaling for computer vision tasks | Laptop, Projector, Cloud
Access | 25:00 | 35:00 | IT/CV/N0805 |
