패키지, 저장소 및 앱 카테고리 검색

GitHub 저장소root458/Plant-Disease-Detector

식물 질병 탐지기

식물의 피해 부위 사진을 기반으로 식물 질병을 감지하는 플러터 앱입니다.

식물 질병 탐지기 프로젝트 이미지
스타
43
포크
18
최근 푸시(UTC)
2022. 2. 16.
프로젝트 상태
활성

원본 README

아래는 영문 원문 스냅샷입니다. 최신 내용은 GitHub에서 확인하세요.

Plant Disease Detector

A Flutter app that detects a plant's disease given a photo of an affected part of the plant.

Visuals

Installation

A Flutter installation is required to run this project. To install Flutter, visit the official installation documentation. Set up an editor of choice as specified here.

Download the project.

git clone https://github.com/root458/Plant-Disease-Detector.git

Run the below command inside the project directory to install necessary packages.

flutter pub get

To run the project in debug mode

flutter run

To generate a release build

flutter build apk

Locate the app-release.apk file from the directory build/app/outputs/flutter-apk/ and install in your Android smartphone or emulator to use.

Usage

On launching the application, you will be presented with the usage instructons. It follows that to get a suggestion of a disease affecting a plant of interest, take a photo of the plant, or select a photo of the plant from your gallery.

The application then runs the TFLITE model in the background to get a suggestion of the disease. It displays the results on the next screen Suggestions

Important to note

  • The tflite model has been trained to detect only a subset of the diseases. They include:

    • Pepper Bell Bacterial Spot
    • Pepper Bell Healthy
    • Potato Early Blight
    • Potato Healthy
    • Potato Late Blight
    • Tomato Bacterial Spot
    • Tomato Early Blight
    • Tomato Healthy
    • Tomato Late Blight
    • Tomato Leaf Mold
    • Tomato Septoria Leaf Spot
    • Tomato Spotted Spider Mites
    • Tomato Target Spot
    • Tomato Mosaic Virus
    • Tomato Yellow Leaf Curl Virus
  • The size of the dataset was only sufficient enough to make the model recognize selected diseases, but it faces problems with images of non-plants.

  • The application was built using Flutter and a tflite model from Teachable Machine Learning by Google. The dataset was from KAGGLE.

Contributing

Contributions towards the project are welcome. Specifically:

  • The tflite model used can be replaced with a more accurate one/one with more diseases.
  • The responsiveness of the application can be improved.
  • Warning messages can be added for non-plant inputs made by users.

License

MIT

Project Status

The requirements I set have been made possible. However, the application can still be improved. Additions/improvements can be made as specified in the Contributing section.

Hope Kagame Opiyo GitHub avatar
GitHub 작성자

Hope Kagame Opiyo ↗

Flutter Software Developer

@OnSpace-TechnologiesNairobi, Kenya
언어DartC++CMakeHTMLCSwiftKotlinObjective-C

분류

의존하는 Flutter 컴포넌트

사용 중인 의존성

의존성 목록 13 개

앱 카테고리

프로젝트에 맞는 저장소를 선택하려면?

사용 목적에 따라 검색하고 개발 활동을 비교한 뒤 원본 저장소에서 요구 사항을 확인하세요.

  1. 이름, 작성자 또는 설명으로 검색하고 기술 주제로 범위를 좁힙니다.
  2. 스타, 포크, 최근 푸시를 함께 비교하세요. 스타는 관심의 지표이며 품질을 보장하지 않습니다.
  3. 사용하기 전에 GitHub에서 README, 라이선스, Issues를 확인하세요.

출처 및 관리

“A repository is the most basic element of GitHub.”

GitHub Docs — About repositories ↗