Mobile Veggie Detector is an Android-based computer vision application designed to identify vegetables in real time using smartphone camera input.
This project combines Android development, Java, OpenCV, and deep learning concepts to support real-time vegetable recognition through a mobile interface.
This project was developed into a published research paper:
Mobile Veggie Detector: Real Time Detection of Vegetables Through Mobile Application and Deep Learning
International Conference on Advanced Computing and Communication Systems (ICACCS), 2024
Role: First Author
🔗 Paper Link: https://ieeexplore.ieee.org/document/10716989/
The goal of this project is to make vegetable identification easier using a smartphone camera.
Instead of manually searching or comparing vegetable images, the app allows users to point the camera at a vegetable and receive a detection result through the mobile app.
| Feature | Description |
|---|---|
| 📷 Real-Time Camera Input | Uses smartphone camera input for detection |
| 🥦 Vegetable Identification | Recognizes vegetable categories from images |
| 📱 Android Application | Built as a mobile app |
| 🧠 Deep Learning Concept | Applies image classification ideas |
| 🔎 Computer Vision Workflow | Processes visual input for prediction |
| ⚙️ OpenCV Support | Includes OpenCV library integration |
Camera Input
↓
Image Processing
↓
Vegetable Detection
↓
Prediction Result
↓
Display on Android App
| Category | Tools / Technologies |
|---|---|
| Programming Language | Java |
| Platform | Android |
| IDE / Build | Android Studio, Gradle |
| Computer Vision | OpenCV |
| AI / ML Area | Deep Learning, Image Classification |
| Application Type | Mobile Computer Vision App |
I worked on this project as the first author and mobile AI project contributor.
My work focused on:
- Developing the Android-based application workflow
- Integrating real-time camera-based vegetable detection
- Applying computer vision and deep learning concepts
- Supporting mobile image classification functionality
- Contributing to the research paper based on the project
- Documenting the system idea, implementation, and results for publication
| Area Tested | Validation Goal |
|---|---|
| Camera Input | Verify camera opens and captures input correctly |
| App Workflow | Confirm navigation and prediction display work properly |
| Image Recognition | Check whether vegetables are classified correctly |
| Model Output | Validate predicted labels shown to the user |
| Mobile Usability | Check app behavior on Android device or emulator |
| Error Handling | Verify app handles unclear or invalid input safely |
Make sure you have:
- Android Studio installed
- Java JDK installed
- Android SDK configured
- Gradle support enabled
- Android device or emulator available
-
Clone the repository.
git clone https://github.com/SHREENITHI-TV/Mobile-Veggie-Detector.git -
Open Android Studio.
-
Select File → Open.
-
Choose the cloned project folder.
-
Let Gradle sync complete.
-
Connect an Android device or start an emulator.
-
Run the application from Android Studio.
| Folder / File | Purpose |
|---|---|
app/ |
Main Android application code |
openCVLibrary3413/ |
OpenCV library integration |
gradle/wrapper/ |
Gradle wrapper files |
build.gradle |
Project-level Gradle configuration |
settings.gradle |
Gradle project settings |
gradlew / gradlew.bat |
Gradle run scripts |
This project demonstrates practical experience with:
- Android application development
- Java-based mobile development
- Computer vision workflows
- Real-time camera-based input
- Deep learning application concepts
- Mobile AI project implementation
- Research-to-application development
- Technical publication experience
- Improve model accuracy with larger training data
- Add confidence score display
- Add support for more vegetable classes
- Publish APK release for easier installation