PRODIGY9 Problem Statements

Recording

PRODIGY9: Problem Statement Sharing Session

PRODIGY9: Problem Statement 1 - Optimize Paper Usage for Sticker Printing Shop

Prize: 3-month internship at PRODIGY9 Co., Ltd. (Bangkok or Remote) and a special CWB edition custom designed scarf

1st place: $350 USD - Microsoft Funded

Context: Sticker Printing Shop trying to optimize its paper usage.

Given:
– An image of irregular shape such as a heart or a butterfly shape.
– Minimum printed size (of the bounding box) in centimeters such as 5cm x 5cm
– 1cm of padding required between borders of images on the same paper.
– 2cm of padding inside the paper.

We would like you help the printing shop saves the number of papers used by developing a solution that will help with laying out the images onto the paper in the most optimized way possible (i.e. as many images on a single paper as possible.)

For example, a perfectly square image can only be laid out one way: by placing them in a regular grid. An equilateral triangle-shaped image can be laid out in alternating upside down pattern (AVAVAV).

The paper size will be A3 which are 297 mm wide and 420 mm long.

Bonus points if:
– Your solution can handle more than one image at once (laying out 2 images in an optimized pattern).
– It can also adds a red outline to each image which are 0.5cm away from the image border. The line will be used by the die cutting machine as a cutting guide.

Tech Stack:
– Azure Machine Learning

Success Criteria:
– Bonus features
– Processing Speed
– Creativity in how the layouts are done
– How AI/ML is used to help with the layout

PRODIGY9: Problem Statement 2 - Create an AI service to compose a new character

Prize: 3-month internship at PRODIGY9 Co., Ltd. (Bangkok or Remote) and a special CWB edition custom designed scarf

1st place: $350 USD - Microsoft Funded

Given a large image dataset from character making websites such as https://storior.com/ or https://picrew.me/en/ which contains images that can be composed together to make a character (for example, swords, shields, helmets for a knight).

We would like you to create an AI service such that when given a prompt, it would select the individual parts from the library of images at your disposal to compose a new character that would best match the given prompt. If no images are available or the AI believes there are not enough data/images available to satisfy the prompt, we would like for it to simply make a suggestion that will most closely match the prompt.A small set of images will be provided for testing.

Tech Stack:
– Azure AI Vision
– Azure OpenAI

Success Criteria:
– Creativity on how the prompt UI is presented.
– Quality of the generated result.
– AI usage costs per prompt

Sponsored by:

Powered by:

Stay connected: