Tesseract OCR
Tesseract is a open-source Optical Character Recognition (OCR) that converts scanned documents or photos into computer-processed texts. It was created as a proprietary software in the 1980s, but was then released as open source in 2005 and sponsored by Google in 2006. This tool has the power to recognize over 100 languages, handle complex layout analysis, and image preprocessing.
The Eviction Lab uses this tool to digitize eviction records, especially from local courts. Considering many eviction filings are PDF documents or handwritten/ typed forms, they are not always standardized, which makes it difficult for a computer to process.
Tesseract OCR corrects this problem by extracting key details such as names, addresses, case numbers, etc. While also adjusting messy scans, leaving reliable and processed data for Eviction Lab to implement.
Additional Uses for Tesseract OCR:
- License plate recognition
- ID scanning
- Text-to- speech apps
Mapbox
Mapbox is a javascript library that provides numerous design tools including ability to create customized maps, visualizations, and geocoding. This platform is developer-friendly, while also allowing the opportunity for a complex way to present data.
The Eviction Lab project uses the Mapbox tool to present an interactive map, which shows statistics for each county across the U.S regarding the number of evictions filed for every 100 renter households. By using Mapbox, Eviction Lab’s data is shown in a clean and professional way, while also making it easy for viewers to obtain the information on evictions from all over the country.
Additional Uses for Mapbox:
- Doordash app
- Real Estate & Housing
- Snapchat: SnapMap feature
Hyperobjekt
Hyperobjekt is an online agency that builds websites and data visualization in order to support researchers. The purpose of this platform is to present information gathered by researchers to the public in the forms of websites and applications. Previously highlighted issues such as eviction, inequality/ poverty, racial justice, and the criminal justice reform. Hyperobjekt have partnered with institutions such as Princeton University, UCLA, Yale, and Stanford.
The Eviction Lab used this tool to design their interactive site that presents the first national dataset of evictions within the United States. After the researchers of Eviction Lab collected their data, it was up to Hyperobjekt to build a website that highlights the issue of housing.
Hyperobjekt has been used for a variety of different websites in order to connect the general public to the real world problems occuring today.
Additional Uses for Hyperobjekt:
Connection to Digital Humanities
Digital humanities is shown thoroughly within The Eviction Lab, where they use tools to display date revolving around humanities such as economics, sociology, and housing policies. The platform Mapbox, especially, was used to create interactive maps in order to present humanistic data for scholars to engage in. Digital humanities is apparent within this platform considering it is combining a computing tool with the rising issue of eviction, while also allowing the public to engage and gain a better understanding.