August 2020    
         
         
 
     
 
  COVID-19
Research and news
FAQs and resources
University updates
 
 
       
 
 
  Vision of the future  
     
  Computer vision is a field of artificial intelligence that trains computers to “see”—to identify, interpret, classify, and then react to visual images. It’s used in facial recognition, self-driving cars, microscope image analysis, and language translation apps. Computer vision is superior to human vision in some ways but inferior in others because our anatomy and the technology of seeing play by different rules.  
     
  Search function  
     
 
Waldo-spotting robot
 
 
     
  This Waldo-hunting robot arm uses a Vision Camera Kit designed for facial recognition.  
     
 
     
 
  This robot can find Waldo in 4.5 seconds.  
 
       
  Medical physicist Maryellen Giger, PhD’85, a pioneer of computer vision in cancer imaging, explains the difference between detection and diagnosis using the Where’s Waldo? books: “Detection is finding things red-and-white striped. Diagnosis is saying the red-and-white thing is Waldo.”  
     
  If a computer can be trained both to spot stripes and then to decide if they’re an umbrella, a beach towel, or in fact Waldo, radiologists can catch—and clinicians can treat—disease earlier. Giger has been working on computer-aided cancer detection and diagnosis for over 30 years.  
     
 
 
 
  Visionary science  
     
 
     
  1  
     
 
UChicago’s Maryellen Giger aims to develop AI tools to analyze chest X-rays and thoracic CT scans to diagnose, monitor, and help treat COVID-19 patients.
 
     
     
     
 
     
  2  
     
 
The Oriental Institute and UChicago’s computer science department are collaborating on a computer vision–based tool designed to translate ancient cuneiform tablets.
 
     
     
     
 
     
  3  
     
 
Astrophysicist Brian Nord uses computer vision to find gravitational lenses—places in space where light is distorted by massive objects, such as planets or galaxies.
 
     
     
     
 
     
  4  
     
 
Rumor has it that image recognition sees giraffes everywhere—but that might be a stretch.
 
     
     
 
         
         
    Spotlight    
         
         
 
     
  In the AI of the beholder  
     
 
Picasso-style Mansueto Library
 
 
     
  Joe and Rika Mansueto Library rendered in the style of Friendship (1908) by Pablo Picasso using the DeepStyle app.  
     
 
     
  A computational artist and a machine learning expert, both UChicago associate professors, built a “style transfer” model, advancing the field of computer vision—and human perception.  
     
  Style transfer programs, like DeepArt and Deep Dream Generator—whose names refer to deep learning—let you render the content of one image in the style of another. You can upload pictures to these websites or download the UChicago team’s free iPhone app, DeepStyle, to try transfer-style filters on your camera.  
     
 
  In case you missed it  
     
 
Flying colors: Some vibrant colors found in nature are a trick of light.
 
 
Ancient DNA: Geneticists are now able to recover DNA from prehistoric remains.
 
 
 
 
 
     
  Support UChicago biological sciences.  
     
 
     
 
  COVID 2025: In the Our World in the Next 5 Years video series, leading scholars discuss how the coronavirus will change our world and what steps are crucial now to shaping that future.

Sign up to receive µChicago monthly.