Skip to content

Repository files navigation

🎨 AI-Powered Image Colorization


🚀 Project Overview

Image Colorization is a Deep Learning-based web application that automatically converts grayscale (black & white) images into realistic color images.

Using a pre-trained Convolutional Neural Network (CNN), the model predicts color information for each pixel and generates visually appealing colorized outputs.

This project combines Computer Vision, Deep Learning, and Web Development to create an interactive and user-friendly image colorization platform.


✨ Key Features

✅ Upload black & white images instantly

✅ AI-powered automatic colorization

✅ Modern drag-and-drop interface

✅ Real-time image processing

✅ Download colorized images

✅ Responsive and attractive UI

✅ Fast and lightweight deployment


🖼️ Application Workflow

Upload Image
      ↓
Image Preprocessing
      ↓
Deep Learning Model
      ↓
Color Prediction
      ↓
Generate Colorized Image
      ↓
Display & Download Result

🧠 Deep Learning Model

This project uses OpenCV's pre-trained Image Colorization model based on the Caffe framework.

Model Files

The model has been trained on millions of color images and learns to predict realistic color distributions from grayscale inputs.


🛠️ Tech Stack

Frontend

  • HTML5
  • CSS3
  • JavaScript

Backend

  • Flask
  • Python

Deep Learning & Computer Vision

  • OpenCV
  • NumPy
  • Caffe Pretrained Model

📂 Project Structure

ImageColorization/
│
├── app.py
├── colorization_deploy_v2.prototxt
├── colorization_release_v2.caffemodel 
├── pts_in_hull.npy
│
├── templates/
│   └── index.html
│
├── uploads/
│
└── outputs/

⚙️ Installation

1️⃣ Clone Repository

git clone https://github.com/yourusername/ImageColorization.git
cd ImageColorization

2️⃣ Create Virtual Environment

python -m venv venv

3️⃣ Activate Environment

Windows:

venv\Scripts\activate

Linux/Mac:

source venv/bin/activate

4️⃣ Install Dependencies

pip install flask opencv-python numpy

▶️ Run Locally

python app.py

Open:

http://127.0.0.1:5000

📸 Sample Results

Original Image Colorized Output
download (1) result

🎯 Skills Demonstrated

  • Deep Learning
  • Computer Vision
  • Image Processing
  • Flask Development
  • OpenCV DNN Module
  • Frontend Design
  • Model Integration
  • Git & GitHub

🔮 Future Enhancements

  • 🎥 Video Colorization
  • 📱 Mobile-Friendly Interface
  • ☁️ Cloud Deployment
  • 📂 Batch Image Processing
  • 🖼️ Before/After Comparison Slider
  • 🤖 Advanced GAN-based Colorization

👩‍💻 Author

Samruddhi Shivtare

GitHub: https://github.com/Samruddhi1517

About

A Deep Learning-based web application that transforms black-and-white images into realistic color images using OpenCV and a pre-trained CNN model.

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages