Wolfram Computation Meets Knowledge

Back to Research-Based Educational Programs

Wolfram High School
Summer Research Program

Formerly known as the Wolfram High School Summer Camp

Bentley University, Boston, MA June 25–July 13, 2024

Alumni

Stella Maymin

Class of 2019

Bio

Stella Maymin is a rising eighth grader at Greenwich Country Day School. She was on the High Academic Honor Roll and High Effort Honor Roll every semester while carrying a full schedule of honors courses. Her hobbies include rhythmic gymnastics, sailing, basketball, and trapeze and silks in circus. She has won the GCDS Tiger Pride Award, the Instructors Sailing Award, #1 Rhythmic Gymnast in Connecticut by USA Gymnastics, one gold and one silver medal from the National Latin Exam, and was a public speaking finalist almost every year since 5th grade. Her self-published book, "What They Don't Teach You on Earth," is a collection of short stories.

Project: Automated Spot the Difference

Goal

I created a website that autogenerates modified images by removing content or editing content and shoving the edited content back into the original image. A user chooses a difficulty level, whether they would like one image or all of the images in that difficulty range and an image. They can click to the very right in order to reveal the correct solution.

Summary of Results

The major problem with creating a function to autogenerate masks was that it automatically assesses textures to Inpaint based on the original image, so in a picture of two elephants, the large elephant would be masked correctly, but Inpaint would include many floating baby elephant heads. To solve this, I had to create a mask for the background so that the contents would be retouched with that instead. I also found that ImageDistance is a great proxy of how humans assess the difficulty of spot-the-difference challenges.

Future Work

As an extension of my website, I would like to find a way to create more of a game, perhaps by using dynamics. Though I played around with LocatorPane, I couldn’t figure out the code to make it work successfully on the web. Other extensions may be to create a timer to show how long it took the user to find the difference or a counter of how many incorrect clicks on the Locator there were. Using the high scores, I think it might be possible to create a leaderboard across all users. Lastly, a simpler stretch goal is to create the option of allowing the user to upload their own images.