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

Let me show some results of the system

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