This repository contains a CBIR (content-based image retrieval) system

Extract query image's feature, and retrieve similar ones from image database

In this system, I implement several popular image features:

• color-based
  • RGB histogram
• texture-based
  • gabor filter
• shape-based
  • daisy
  • edge histogram
  • HOG (histogram of gradient)
• deep methods
  • VGG net
  • Residual net

Some features are not robust enough, and turn to feature fusion

• fusion.py

The curse of dimensionality told that vectors in high dimension will sometimes lose distance property

• Random Projection

CBIR system retrieves images based on feature similarity

Robustness of system is evaluated by MMAP (mean MAP), the evaluation formulas is refer to here

• image AP : average of precision at each hit
  • depth=K means the system will return top-K images
  • a correct image in top-K is called a hit
  • AP = (hit1.precision + hit2.precision + ... + hitH.precision) / H
• class1 MAP = (class1.img1.AP + class1.img2.AP + ... + class1.imgM.AP) / M
• MMAP = (class1.MAP + class2.MAP + ... + classN.MAP) / N

Implementation of evaluation can found at evaluate.py

My database contains 25 classes, each class with 20 images, 500 images in total, depth=K will return top-K images from database

Display on website using Flask Run on terminal : python flask/app.py

If you are interesting with the results, and want to try your own images,

Please refer to USAGE.md

The details are written inside.

Po-Chih Huang / @pochih