README.md

metadata

language: en
license: mit
tags:
  - image-classification
  - face-shape
  - tensorflow
  - mobilenetv2
base_model: google/mobilenet_v2
datasets:
  - niten19/face-shape-dataset
metrics:
  - accuracy
model-index:
  - name: face-shape-classifier
    results:
      - task:
          type: image-classification
        dataset:
          name: face-shape-dataset
          type: niten19/face-shape-dataset
        metrics:
          - type: accuracy
            value: 0.63

Face Shape Classifier

Project Overview

AI-powered app that detects face shape from photo and suggests best hairstyle.

Model Details

• Architecture: MobileNetV2 (Transfer Learning)
• Framework: TensorFlow/Keras
• Validation Accuracy: 63%
• Epochs: 25

Dataset

• Source: Kaggle - niten19/face-shape-dataset
• Classes: Heart, Oval, Round, Square, Oblong
• Training Images: 4000
• Testing Images: 1000

Tech Stack

• Python
• TensorFlow
• MediaPipe
• OpenCV
• Streamlit

ML Pipeline

1. Photo Upload
2. Face Detection (MediaPipe)
3. Face Shape Classification (MobileNetV2)
4. Hairstyle Recommendation
5. Virtual Try-On Overlay