Skip to content

Keep your pets safe! Upload a picture and obtain a flowers toxicity levels with the click of a button.

Notifications You must be signed in to change notification settings

flrivera/Pet-Lab

Repository files navigation

Pet-Lab:

Flower Classification and Toxicity Information App

Overview

This app leverages a classification model created using ImageNet and transfer learning. For model information look at the github pages, for the model itself e-mail me at [email protected].

Pet-Lab is an innovative application designed to help pet owners keep their pets safe. By simply uploading a picture of a flower, users can obtain toxicity levels with just a click of a button. The app identifies flowers based on unique characteristics, categorizing them into five types. It then searches a database to provide users with toxicity information, including severity and common symptoms, as well as a flower description to aid in detection confirmation.

Table of Contents

InstallationUsageFeaturesContributingLicense

Installation

Available through Streamlit.

Clone repo and use ‘streamlit run Recog_app.py’

Project Structure

  • Recog_app_AWS_call.py: uses s3fs to both save and retrieve ml models as zip files. Taken from https://gist.github.com/ramdesh keras_model_s3_wrapper.py
  • remove_image_background: Contains functions for background removal using OpenCV. Python function that takes an image file path as input, removes the background of the image, and saves the resulting image with a transparent background. It utilizes the OpenCV library to perform image processing operations.
  • decode_and_resize.py: Implements image decoding and resizing operations.
  • toxicity.py: handles the web scrapping for pet toxicity info of classified flowers using https://www.aspca.org/pet-care/animal-poison-control/toxic-and-non-toxic-plants
  • Recog_app.py: The main application file that integrates the functionalities from other files.

Usage

  1. Upload a picture using the Pet-Lab app.
  2. Using Classification Model saved from AWS classify the flower in the picture
  3. Click the button to obtain toxicity levels.
  4. Receive information about the identified flower, including toxicity severity and common symptoms.

Features

Pet-Lab offers the following key features:

• Flower identification into 5 types based on unique characteristics. • Database search for toxicity information, including severity and symptoms. • Background removal of images. • Utilization of the Inception v3 architecture pretrained on ImageNet.

Contributing

We welcome contributions to enhance Pet-Lab. To contribute, follow these steps:

  1. Fork the project.
  2. Create a new branch (git checkout -b feature/your-feature).
  3. Commit your changes (git commit -m 'Add some feature').
  4. Push to the branch (git push origin feature/your-feature).
  5. Open a pull request.

License

Pet-Lab is licensed under the MIT License - see the LICENSE file for details.

About

Keep your pets safe! Upload a picture and obtain a flowers toxicity levels with the click of a button.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages