Plant Species Classification Model
Model Description
This is a deep learning model for automated classification of flower species using computer vision. The model can identify 5 common flower types with high accuracy.
Model type: Image Classification
Architecture: EfficientNetB0 with custom classification head
Input: 224×224 RGB images
Output: 5-class classification probabilities
Intended Uses
Primary Use Cases
- 🌿 Educational plant identification tools
- 📱 Mobile flower recognition applications
- 🔬 Botanical research and biodiversity monitoring
- 🌸 Gardening and nature enthusiast apps
Limitations
- Trained on only 5 specific flower species
- Performance may vary with image quality and lighting conditions
- Not suitable for rare or unusual flower varieties
Classes
The model classifies images into 5 flower species:
- daisy 🌼 - Classic white petals with yellow center
- dandelion 🌞 - Bright yellow composite flowers
- rose 🌹 - Layered petals in various colors
- sunflower 🌻 - Large yellow flowers with dark centers
- tulip 🌷 - Cup-shaped flowers in vibrant colors
Training Data
- Dataset: Flowers Recognition from Kaggle
- Total Images: ~4,300
- Split: 80% training, 20% validation
- Augmentation: Rotation, flipping, zooming, brightness adjustment
Performance
- Validation Accuracy: >90%
- Inference Speed: Real-time capable
- Model Size: ~30MB
Usage
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
import numpy as np
# Load and use the model for flower classification
model = load_model('flower_classification_model.h5')
Input Requirements:
- Image format: JPEG, PNG
- Image size: 224×224 pixels
- Color mode: RGB
Ethical Considerations
- Intended for educational and research purposes
- Should not replace expert botanical identification
- Respect privacy when deploying in applications
Citation
If you use this model in your work, please cite:
Plant Species Classification Model by Athar Abbas
https://huggingface.co/AtharAbbas993/Plant_Species_Classification