potterhsu/SVHNClassifier

A TensorFlow implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)

49
/ 100
Emerging

This helps automatically recognize multi-digit house numbers from street-level images. You provide an image containing house numbers, and it outputs the identified digits. This is useful for urban planners, mapping services, or researchers analyzing urban environments.

210 stars. No commits in the last 6 months.

Use this if you need to accurately extract house numbers from photographs of buildings or street views.

Not ideal if you're looking to recognize general objects or text in images, or if your images are not street-level house numbers.

urban-planning image-analysis mapping-services street-data number-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

210

Forks

72

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

May 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/potterhsu/SVHNClassifier"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.