Code Monkey home page Code Monkey logo

cvit-workshop's Introduction

Codes for all the tasks done in the workshop on Computer Vision

Notes for the workshop are written at this notion doc

Have the following packages installed to run the programs:

pip install numpy
pip install opencv-python
pip install dicom
pip install pydicom
pip install scipy
pip install scikit-image
pip install torch
pip install torchvision

Also, feel free to make a pull request if you find any bugs in the code, since it is my first time doing this, I am sure there will be a lot of bugs.



Short rundown of tasks done on each day:

Day 1

Session 1 (Basics)

- Intro to Python Notebooks
- Intro to Python
- Intro to Numpy
- Intro to Image Processing ( OpenCV )
    - Importing and
    - Chroma Keying
    - To be Done - Frequency Histogram
    - To be Done - Thresholding

Session 2 (Barcode Detection and Scanning)

- Sobel Filters
- Bar Code Detection and Scanning
- Learning about EAN-13 Barcode System
- Thresholding Methods
    - Global Threshholding (using same threshold for all pixels)
    - Adaptive Threshholding (using different threshold for different pixels)

- HW
    -Find seed fill algorithm (similar to DFS)
    - Sobel Filters

Day 2

Task 1 (Document Imaging)

- Intro to Document Imaging
- Hands-on Task
    - Canny Edge Detection
    - Hough Line Transform
    - Skew Correction
        -(Not aligned with the horizontal axis)
        - Correction by Rotation
        - Rotation of a document image from its intended orientation
        - Reduces the acuracy of OCR
    - Line And Word Detection
    - Reading Check Number

    - HW : try root(sobelX^2 + sobel^2) and compare with Canny
    - Non-Maximal Suppresion

Task 2 (Word and Line Segmentation)

Task 3 (Cheque Number Reader)

- Understanding the nomeclature of a cheque
- Smoothing techniques
- Removing noise and borders
- Intro to OCR (by template matching)
- Sobel Filters
- Black Hat Transform

Day 3

Session 1 (Convex Optimization)

- Intro to Convex Optimization
- Using CVXOPT library
- Solving Knapsack Problem
- Smoothing graph using Convex Optimization
- Realtime Application of smoothing boxes in video

Session 2 (Medical Imaging)

- Windowing for different parts of the body
- Parallel Beam Tomographic Reconstruction using Simple Backprojection

Day 4

Session 1 ( 3-D )

- Intro to 3D
- PyMesh
- Open3D
- ICP

Session 2

- Blender

Day 5

Sesion 1 (Basics of ML)

- Basics of ML
- K- Nearest Neighbours
- K-Means Clustering
    - Distance Metrics

- Linear Decision Boundaries
    - Loss function 
    - Minimizing the loss fucntion with respect to the parameters (weights)
    - Gradient Descent
        - Different Loss Functions for Gradient Descent


- Neural nets
    - Basics

- Formula for neural nets $\sum_{i=1}^n(w_ix_i + b)$
- Activation Functions

Session 2

- Classifier for a small dataset
- Face detection
- Face Recognition

Day 6

Session 1

- Basics of Research (more on notion page)

Session 2

- Intro to experiment tracking with W&B
    - Basics
    - Sweeps
    - Other features
- Multi- threading and multi-processing using concurrent.futures
- Image captioning
    - Multi-modality

<<<<<<< HEAD

Day 7

Session 1

- Intro to Conv Nets
    - Basics
    - Convolutions
    - Different Architectures
    - Hands-on with MNIST
- Play learning rate, batch size, different datasets

=======

cvit-workshop's People

Contributors

mhardik003 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.