cqtan / imi-unicorns Goto Github PK

HTW IMI-Project: Chasing Unicorns and Vampires in a Library ---> Check the Wiki

Python 70.27% Ruby 0.09% JavaScript 0.07% TypeScript 9.65% HTML 1.53% CSS 18.38%

imi-unicorns's Introduction

Chasing Unicorns and Vampires in a Library

Installation

This application contains 2 parts, one is the Flask server which will serve the http calls and the angular application. The second part is the Angular 2 (Version 6 at this point) which will provide the frontend for this project. To get the Application running follow the steps belowe.

Download the Repository

git clone [email protected]:CouchCat/imi-unicorns.git

and go into the Application Folder

cd imi-unicorns

Database

To restore or create the Database excute the command:

mongorestore -d unicorns ./UnicornsDB/unicorns

Angular 2 (Web application)

Go into the Application Folder:

cd WebApp

and install all dependencies

npm install

for development run:

npm start

for test purposes build the application once with:

npm run build

for production builds, minified and uglyfied:

npm run prod

Python Flask (Server)

Next go back into the root directory

cd Server

create a Python virtual environment

python -m venv .

and install the dependencies of python with:

pip install -r requirements.txt

export the flask application to a enviroment variable:

export FLASK_APP=app/__init__.py

and run the server with:

flask run

the server will be available on:

localhost:5000

imi-unicorns's People

Contributors

Stargazers

Watchers

Forkers

elektrobohemian

imi-unicorns's Issues

Showtime Projektbeschreibung

Test: Real SBB images on our Webapp

Upload the image data to our MongoDB and display images referenced by them on the Webapp.

ML: by Date

Classify images according to their creation date (Time line feature)
Also show for each visualisation.

Wrapping-Up: Create documentation

Create documentation in a way that other uses are able to run the app locally

Try making a wiki page for easy collaboration.
Reduce required libs as much as possible
Include requirements.txt and/or package.json file
Add version of used technologies (only the main ones, e.g. Angular, Keras, etc.)

DB: Add new data for images in the DB

Create a file format (JSON) to add more data for each image in the databank.
Possible data:

people
map
text
animal
etc...

Showtime: T-Shirts

Decide on T-shirt design and order them

Extend dominant color script

Calculate most different and frequent colors

ML: Bag of Visual Words -> Agglomerativ

Ich würde mich mal gerne mit diesem Ansatz hier beschäftigen. BovW

Neu
Agglomerativen Ansatz mit Bag, um Feature Vektoren zu sammlen (Bildähnlichlkeiten)

Feature extraction with pre-trained CNN

ML: Clustering

Research Clustering Methods

Script: DataProcessing

Errors beseitigen und Notebook in ein vernnftiges Script umwandeln. Evtl. auf verschiedene Funktionen aufteilen

ML: Dominant color

Classify images according to their dominant color.

Test: Huge number of images

Test prototype with a larger number of images.

Download needed parts of mets mods

Test: Category Feature

Test feature to filter images by their content:

Drop Down GUI to select one of the following:
- select person
- select maps
- select text
- etc.

Showtime: Test-run our WebApp for showtime!

Make a stable version of our WebApp and perform a test run!

ML: Filter out less-meaningful images

Images, such as covers, blank pages, etc. should be clustered and filtered out so that mostly meaningful images can be displayed and to reduce the number of images in total to handle.

ML: Object Recognition for Category Feature

MIttels Object Detection bestimmte Objekte in den Bilder erkennen:

Person
Animal
- Dog
- Cat
- Unicorn
Building
Plant

ML: Transfer Learning for Category Feature

Verwende gerade 4 pre-trained models aus Keras, die eng mit ImageNet arbeitet.
- https://keras.rstudio.com/articles/applications.html
- Models: VGG16, ResNet50, Inception v3, MobileNet
Diese models haben zumindest 1000 verschiedene Klassen, aber ich muss noch schauen, welche der 4 bessere Performance bietet.
NEU: Transfer Learning für nur eine handvolle verschiedene Klassen

Showtime: Create our Logo

Get our new logo approved!

ML: JSON structure for image feature

# Test with 10 images:

new Collection for each Image
{
  features: <List>
  path: <string> -> ("dist/ChasingUnicornsAndVampires/assets/images/" + PPN + <imageName.ending>) 
  PPN: <string>
}

Insert for every Book
{
 "PPN-Nr": <List of Features>
 "PPN-Nr": ...
  ...
}

For Category
{
  feature: <Collection>(Category: featureName)
}

Overview could be impoved when too many books are in same place
Try displaying as list?