Skip to content

DynImagic.md

Latest commit

 

History

History
58 lines (41 loc) · 2.66 KB

DynImagic.md

File metadata and controls

58 lines (41 loc) · 2.66 KB

Internship Assignment: DynImagic

Objective

Create a Mobile application that utilizes AI to separate colors from a group image and generate individual images with the same pattern. Implement a user-friendly UI to display available designs and colors, allowing users to generate specific color images on demand.

Requirements

  1. Image Processing with AI:

    • Develop a function that takes two images as input: one with the pattern/design and another with a group of colors and patterns.
    • Use AI/image processing techniques to identify and separate different colors from the group image.
    • Generate separate images for each color, preserving the original pattern.

  2. User Interface (UI):

    • Utilize a GUI library like Tkinter, PyQt, or any of your choice for the user interface.
    • Display a list of available designs along with the count of unique colors for each design.
    • When a user clicks on a design, dynamically show the associated colors and patterns.
    • Provide a button or interactive element to generate individual color images based on the user's selection.

  3. GitHub Repository:

    • Set up a GitHub repository for the project.
    • Structure the repository with appropriate directories (e.g., code, documentation).
    • Include a README file with instructions on how to run the application, required dependencies, and any additional information for users and developers.

  4. Documentation:

    • Document your code thoroughly.
    • Provide a brief explanation of the AI/image processing techniques used.
    • Clearly explain the structure of your UI and how it interacts with the image processing functions.

Submission

  1. Push the complete codebase to the GitHub repository.
  2. Include a README.md file with clear instructions on how to set up and run the application.
  3. Provide a short document explaining the AI techniques used for color separation.

Evaluation Criteria

  1. Functionality (50%):

    • Successful color separation and image generation.
    • User-friendly UI with design and color selection features.

  2. Code Quality (30%):

    • Well-documented code.
    • Clear and modular structure.

  3. GitHub Repository (10%):

    • Proper organization of files and directories.
    • A README file with comprehensive instructions.

  4. Documentation (10%):

    • Concise documentation explaining the AI techniques used.
    • Clear instructions for users and developers.

Note

Feel free to use any libraries or frameworks you find suitable for image processing and UI development. The goal is to create a functional and well-documented application that meets the specified requirements.

© 2023 RecursiveZero, All rights reserved.