anhhuynh1506 / Instanced-Level-image-retrieval-with-DeLF

An image retrieval system with DeLF

Instanced-Level-image-retrieval-with-DeLF

Group member:

• Nguyen Hoang An - [e-mail]
• Nguyen Huynh Anh - [e-mail]
• Duong Trong Van - [e-mail]

Table of contents

=================

• Introduction
• Install requirements
• Data
• Demo
• Checklist
• Run code

Introduction

This project is on the field of Computer Vision, an sub-domain of Computer Science. On this project, we build our image retriveval system based on the famous paper public in ICCV 2017: Large-Scale Image Retrieval with Attentive Deep Local Features.

Evaluation our system by Average Precision and Mean Average Precision

Futhermore, we use Flask - an web framework using for python to build our GUI

Install requirements

pip install -r requirements.txt

Data

Our data is around 1300 landscape images of 20 class from Google Landmarks Dataset v2

Demo

Main screen

Example

Run code:

Extract Database (if you update or create new database):

python extract.py

To run main code:

python server.py

Output:

* Serving Flask app "server" (lazy loading)
 * Environment: production
   WARNING: This is a development server. Do not use it in a production deployment.
   Use a production WSGI server instead.
 * Debug mode: off
INFO:werkzeug: * Running on http://127.0.0.1:5000/ (Press CTRL+C to quit)

Go to http://127.0.0.1:5000/

Checklist

• Upload Image
• Process uploaded image
• Save Image to Database
• Interactive Web app
• Retrieve Image
• Average Precision and Mean Average Precision
• Optimize processing time