Skip to content

Content Based Image Retrieval System Implemented Using Python, Flask And OpenCV.

License

Notifications You must be signed in to change notification settings

kudeh/image-search-engine

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

51 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image-Search-Engine

Content-Based Image Retrieval System Implemented Using Python, Flask And OpenCV.

  • Given a query image, this app returns other images from database in order of similar color content.
  • Uses a color histogram to define the color content of an image, uses chi-squared distance to determine how similar two image histograms are.

Usage Guide

  1. To use a different image dataset (optional)

    • Populate image DB in app/static/images
    • Then in Terminal:
      >> python3 -m venv venv
      >> source venv/bin/activate
      >> pip install -r requirements.txt
      >> cd app
      >> python index.py --dataset static/images --index index.csv
  2. Run locally using Docker

    • Install Docker
    • Then in Terminal:
      >> docker build --tag=imagesearch .
      >> docker run -p 80:8000 imagesearch
  • You should be able to access app at localhost:80 in browser

Sources

Project was made possible thanks to the many guides provided by @Adrian Rosebrock on pyimagesearch.com