ai-ml-task

Instructions:

1. Fork the github repo into your personal Github account and take a clone into your local system.

   Guide to Forking Github Repo: https://docs.github.com/en/github-ae@latest/get-started/quickstart/fork-a-repo

   Guide for cloning Github Repo: https://docs.github.com/en/repositories/creating-and-managing-repositories/cloning-a-repository

2. Instantiate Virtual Studio code or any Development environment of your choice to complete the assessment in your local working directory.

3. Save the files and push it into forked Github github repo.

   Guide to pushing code into Github Repo: https://docs.github.com/en/migrations/importing-source-code/using-the-command-line-to-import-source-code/adding-locally-hosted-code-to-github

4. Record a screencast video recording demonstrating the solution in your system and upload the video into the forked github repo.

   Guide to record screen in

   a) MAC: https://support.apple.com/en-in/102618

   b) Windows: https://www.microsoft.com/en-us/windows/learning-center/how-to-record-screen-windows-11

   c) Ubuntu: https://askubuntu.com/questions/4428/how-can-i-record-my-screen

5. Share the repository link into the Google Form: https://forms.gle/2HbLP8GNiYArZFsj8

Problem Statement:

You are given an image which contains multiple headings and subheadings, perform suitable preprocessing techniques and computer vision approaches to extract the text in an organized format, write the python code to take the image input and create the organized dictionary as output.

Sample Input and output

Input

Output

{
  "Ashoka Chakra": "Dharma Chakra (Wheel of Law)",
  "Saffron": "Represents strength and courage",
  "Green": "Represents fertility, growth, and auspiciousness of the land",
  "White": "Symbolizes peace and truth"
}

The Task

• Take the Image sample.jpeg present in this repository
• create a dictionary containing headers as keys and content as value
• submit the output screenshot
• write the readme on the approach that you followed

Our aim is to assess applicants' aptitude, innovative thinking, and their ability to comeup with new ways of solving problems, its an open ended assessment and candidate is free to innovate new ways of preprocessing or organizing the texts.

Deliverables:

• python script to take in image and output dictionary
• readme explaining steps to run the code
• readme explaination on the approaches followed
• demo video showing the output

Push the source code along with a demo video of your solution into the forked github repo. Share the repo link in the google form: https://forms.gle/2HbLP8GNiYArZFsj8