Humans of Paris 1900: Difference between revisions

From FDHwiki
Jump to navigation Jump to search
No edit summary
No edit summary
Line 11: Line 11:
== Implementation ==  
== Implementation ==  


== Project plan ==
== Project execution plan ==
The final goal is to present the user with a way to navigate the collection and understand who the people is the photos are and what life they lived. We develop a website that provides the user with 4 core functionalities.
 
<ol>
<li>
An overview of the most famous individuals in the collection
</li>
<li>
A search page to explore individuals based on tag matching
</li>
<li>
A cluster view of individuals in the database, based on their looks
</li>
<li>
A way to upload ones image and find ones’ doppelgänger in the collection
</li>
</ol>
 
To make this vision reality, we went through 4 stages in the processing, namely fetching the data, processing it, storing and serving data and front end development.
 
The fetching can easily be done using the [http://fdh.epfl.ch/index.php/Gallica_wrapper wrapper] provided by Raphaël Barman.
<ul>
<li>
Preprocessing involves processing of the metadata to extract tags as well as processing of the images to obtain a vector encoding of an individual's face using [http://cmusatyalab.github.io/openface/ OpenFace], extracting [https://pypi.org/project/py-agender/ age and gender using the pyAgender python library] and cropping it using [https://pypi.org/project/opencv-python/ OpenCV].
</li>
<li>
Storing the data involves [https://www.sqlite.org/index.html Sqlite] and Django ORM [https://docs.djangoproject.com/en/2.2/topics/db/ Django ORM]
</li>
<li>
Serving the data: [https://www.djangoproject.com/ Django]
</li>
<li>
Front end development uses [https://getbootstrap.com Bootstrap] to enable quick and beautiful UI design and [https://d3js.org/ D3.js] for displaying the FaceMap.
</li>
 
We organized the tasks according to the following schedule and milestones.


=== Milestones ===
=== Milestones ===

Revision as of 12:20, 12 December 2019

Motivation

We take inspiration from the famous Instagram page, Humans of New York, which features pictures and stories of people living in current day New York. In similar fashion, our project, Humans of Paris, has the aim to be a platform to connect us to the people of 19th century Paris. Photography was still in its early stages when Nadar took up the craft in his atelier in Paris. Through the thousands of pictures taken by him and his son we can get a glimpse of who lived at the time. We explore the use of deep learning models to cluster similar faces to get an alternative, innovative view of the collection and allowing for serendipitous discovery of patterns and people. There is a story behind every person, and our interface highlights this by association people’s story with their picture.


Historical Background

Implementation

Project execution plan

Milestones

Weekly working plan
Timeframe Task Completion
Week 4
07.11 Understanding Gallica Query Gallica API ✓
Query Gallica API
Week 5
14.10 Start preprocessing images ✓
Choose suitable Wikipedia API
Week 6
21.10 Choose face recognition library ✓
Get facial vectors
Try database design with Docker & Flask
Week 7
28.10 Remove irrelevant backgrounds of images ✓
Extract age and gender from images
Design data model
Extract tags, names, birth and death years out of metadata
Week 8
04.11 Set up database environment ✓
Set up mockup user-interface
Prepare midterm presentation
Week 9
11.11 Get tags, names, birth and death years in ready-to-use format ✓
Handle Wikipedia false positives
Integrate face recognition functionalities into database
Week 10
18.11 Create draft of the website (frontend)
Create FaceMap using D3
Week 11
25.11 Integrate all functionalities
Finalize project website
Week 12
02.12 Write Project report
Retrieved from "http://fdh.epfl.ch/index.php?title=Humans_of_Paris_1900&oldid=3716"