Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/captaincodercool/multimodal-search-engine-with-text-and-image-embedding-retrieval

This project builds a multimodal search engine that allows users to query using both text and images. It uses CLIP-based embeddings to index and compare visual and textual data in a shared vector space, enabling intelligent retrieval of relevant content regardless of input format. Ideal for media, e-commerce, and document discovery.

https://github.com/captaincodercool/multimodal-search-engine-with-text-and-image-embedding-retrieval

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (7.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

This project builds a multimodal search engine that allows users to query using both text and images. It uses CLIP-based embeddings to index and compare visual and textual data in a shared vector space, enabling intelligent retrieval of relevant content regardless of input format. Ideal for media, e-commerce, and document discovery.

Basic Info
  • Host: GitHub
  • Owner: CAPTAINCODERCOOL
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 6.44 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme

README.md

Multimodal Search Engine

A multimodal search engine using text and image based search using algorithms TF-IDF, Word2Vec, SIFT and Bag of Visual Words. It shows closely related words and images when given a word or image as input. Search Engine data contains articles of 100 choosen words from wikipedia and 50 images per word downloaded from google images.

Required Packages

Following python packages are required:

Pillow opencv pickle scikit-learn SciPy time pandas JSON Beautiful Soup RegEx Natural Language Toolkit Urllib glob pathlib Gensim sys OS Selenium hashlib Tkinter ipynb webbrowser

For downloading images or web-scrapping images, chromedriver.exe is required to crawl through the images from google search and download the images.

Algorithms

  • TF-IDF and Word2Vec for text based Search
  • SIFT and bag of visual words for image based search

How to run

Run searchenginegui.ipynb in jupyter to start gui for the search engine.

Owner

  • Login: CAPTAINCODERCOOL
  • Kind: user

GitHub Events

Total
  • Push event: 2
  • Create event: 2
Last Year
  • Push event: 2
  • Create event: 2