Mentor/s
Tolga Kaya Richard Errico
Participation Type
Poster
Abstract
This project aims to develop a camera that prints AI-written poems about photos taken. The system features a custom-designed 3D-printed case with a battery pack for mobility, a five-inch touch screen to allow the user to see what they are taking a picture of, and a high-quality Raspberry Pi camera for adjustable photos. To allow for different styles of poems, a web application using Flask was created. The Python program utilizes OpenAI and Replicate to analyze the photo taken, create a descriptive caption, and create a poem. The different poem styles include Limerick, Haiku, Standard, Dream-Like, Future, Sonnet, and Acrostic. Once the user selects the poem style, a live stream of the camera can be seen on the five-inch display. The program then waits till the user presses the shutter button to close the live stream and then prints the poem. The system resets once the poem is printed so that a different poem style can be selected. This camera overcomes previous limitations by allowing the user to see what they are taking a picture of. Overall, this abstract seeks to provide a comprehensive understanding of the development of an AI-driven poetry camera.
College and Major available
Computer Engineering BS, Computer Science BS
Academic Level
Undergraduate student
Location
Digital Commons & West Campus West Building University Commons
Start Day/Time
4-25-2025 12:00 PM
End Day/Time
4-25-2025 2:00 PM
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Prize Categories
Best Visuals, Most Creative, Best Technology Prototype
Poetry Camera
Digital Commons & West Campus West Building University Commons
This project aims to develop a camera that prints AI-written poems about photos taken. The system features a custom-designed 3D-printed case with a battery pack for mobility, a five-inch touch screen to allow the user to see what they are taking a picture of, and a high-quality Raspberry Pi camera for adjustable photos. To allow for different styles of poems, a web application using Flask was created. The Python program utilizes OpenAI and Replicate to analyze the photo taken, create a descriptive caption, and create a poem. The different poem styles include Limerick, Haiku, Standard, Dream-Like, Future, Sonnet, and Acrostic. Once the user selects the poem style, a live stream of the camera can be seen on the five-inch display. The program then waits till the user presses the shutter button to close the live stream and then prints the poem. The system resets once the poem is printed so that a different poem style can be selected. This camera overcomes previous limitations by allowing the user to see what they are taking a picture of. Overall, this abstract seeks to provide a comprehensive understanding of the development of an AI-driven poetry camera.
Students' Information
Julia Piascik, Honors Computer Science and Computer Engineering Student, graduating May 2026.