Skip to content

abhishekmangla/Google-Image-Query-Optimizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Google-Image-Query-Optimizer

This program takes in 2 image queries. The first one is the baseline image query. The second one is a query which is used to compare the first one against. The difference between simply querying Google Images and using this program is this program uses structural similarity of images using image manipulation in SciKit to figure out the best IMAGE REPRESENTATION of your query compared to all the responses retrieved, while Google Images uses PageRank or essentially popularity indexes to give you the most relevant images to your query. That is why this program is an optimized version of Google Image Querying.

Getting Started

You can install the package with pip3 install google-image-query-optimizer. You might want to prepend sudo to that line. You can now run the script with "google-image-query-optimizer".

If you do not install using pip, you can also download this repo and do the following: You might have to install the following: pip3 install numpy pip3 install Pillow pip3 install -U scikit-image

To run: python3 genart.py

Prerequisites

pip3 install numpy pip3 install Pillow pip3 install -U scikit-image

Example

Input

Enter Google Image Query (GIQ): Iron Man

Image Identifier (second GIQ): professional classy

Output

Expected Output or Image that will open is collage of top 3 most representative responses to what you queried:

Alt text

Built With

  • SciKit - Structural similarity
  • Hardikvasa - Downloading images from Google
  • PIL - helps with dealing with images, opening them, resizing etc.

Authors

  • Abhishek Mangla

About

searching images based on image content similarity rather than PageRank

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages