Skip to content

santoshvutukuri/MUST_ACADEMY-Computer_Vision

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MUST_ACADEMY-Computer_Vision

Code repo for MUST Academy - Image Processing and Computer Vision Module

Session Plan:

Hour 1: Getting started with computer vision (Introduction and Setup – 10 mins)

  1. Images as Functions and Matrices. (10 mins)
  2. Mathematical operations with images (15 mins)
  3. Image Filtering (10 mins)
  4. Noises In Images (5 mins)
  5. Image Transformations (8 min)

Challenge 1 – Creating transparent pencil sketch portraits from original images.

Break – 2 mins

Hour 2: Computer Vision ImageOps

  1. Edge Detection (15 mins)
  2. Colour Masking (10 mins)
  3. Template Matching (15 mins)
  4. Shape Detection (15 mins)

Challenge 2 – Traffic Sign Detector from animated and real-world images.

Break – 5 mins

Hour 3 – Computer Vision ImageOps 2

  1. Convolution vs Correlation (10 mins)
  2. Image Binarization (15 mins)
  3. Image Morphology (15 mins)
  4. Image Boundary Issues (10 mins)

Challenge 3 – Localization of bar codes and QR codes in images.

Break – 10 mins

Hour 4 – Exploring the world of deep learning

  1. Introduction to CNNs (15 mins)
  2. Multi-Class Classification using Images (20 mins)
  3. Advanced computer vision deep learning concepts – Neural Style Transfer and GANs (10 mins)

Challenge 4

  • a - Brain haemorrhage segmentation from CT Scan Images using Mask RCNN
  • b - Object tracking from video - Track the cricket ball from the given video

End Note and Q&A – 15 mins

For any queries, feel free to reach out: https://www.linkedin.com/in/aditya-bhattacharya-b59155b6/

Follow me @: https://aditya-bhattacharya.net/

Reference and Learning Resources:

  1. https://opencv.org/
  2. Udacity
  3. https://www.deeplearning.ai/

About

Code repo for MUST Academy - Image Processing and Computer Vision Module

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 55.9%
  • HTML 44.1%