Skip to content

Pet Finder: a web app for pet face detection. Uses the Google Cloud Vision API.

Notifications You must be signed in to change notification settings

ilee38/mlh-local-hack-day

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Major League Hacking's Local Hack Day @ UTSA

A 12-hour hackaton across several countries and schools. More info on Local hack day's website

Project Description

Pet Finder: a web app for pet face detection.

Motivation:

Surveillance cameras are now able to use AI software to identify individuals on public places. The motivation behind this project is to use this technology to find missing pets.

Details:

The Google Cloud vision API was used to quickly provide a description of the contents in an image. No need to train my own neural network!!! 😅 On the back-end, NodeJS was used to create the simple web app. Bootstrap was also used for some quick formatting.

An image of a pet is sent through a request to the API, and a response is received containing a description (e.g. "dog" or "cat") and a score value from 0 to 1, which indicates the level of confidence (1 = 100% confident) for each description.

End of day status:

The app is running with 3 sample images. It sends the request to the vision API and displays the descriptions and confidence levels as a list for each image.

Future Work

  • Need to add an HTML form or other means to allow the user to upload their own images.
  • In order to recognize a particular pet, a database of pets would be necessary. I.e. the problem is not just recognizing an animal in a picture, but recognizing a specific animal/pet.
  • Would be nice to also make it a mobile app.

About

Pet Finder: a web app for pet face detection. Uses the Google Cloud Vision API.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published