Retail / Project story
A shelf view that becomes a count.
A mobile-accessible product detection and classification workflow deployed on Google Cloud.
The challenge
Product recognition for retail teams.
Retail teams needed a way to obtain product counts from shelf images instead of counting each item manually.
YOLOv8 · PyTorch OpenCLIP · Google Cloud
The approach
How the workflow comes together.
- 01
Capture a shelf
Submit an image through the mobile interface.
- 02
Detect and classify
Use trained object detection and visual embeddings to identify products.
- 03
Return the count
Provide product classifications and counts through an API.
Project scope
Built for the task.
This story describes an individual project. Scope and results depend on the inputs, environment and requirements of each implementation.
- Product detection
- SKU classification
- Mobile interface
- Count results via API
Thinking about a similar workflow?
Let’s explore your version.
A practical place to start
What could your
next workflow look like?
Bring us the process. We’ll help you explore the possibilities.
Discuss your project