Fabric_Textile_Cloth_Defect_Detection_and_Classification

🧵 Fabric Textile Cloth Defect Detection & Classification 🚀

🔍 AI-Powered Defect Detection | AI-Powered Textile Quality Control | 🏆 Machine Learning & Deep Learning | Flask Web App | 📊 Data Science | 👕 Textile Industry Innovation

A deep learning-based system for detecting and classifying defects in fabric, textile, and cloth materials using computer vision.

---

📌 Project Overview

This project automates fabric defect detection using machine learning and provides a user-friendly web interface for real-time predictions. It enhances quality control in the textile industry by integrating advanced AI models with an interactive website.

Key Features:

✅ Detects and classifies fabric defects using deep learning models.
✅ Provides a web interface for uploading fabric images and viewing results.
✅ Includes user authentication for secure access.
✅ Offers dynamic pages for contact, feedback, and project information.

---

🛠️ Tech Stack

Technology	Purpose
Python	Core and Backend Development
Flask	Web Framework
SQLite	Database for User Authentication
TensorFlow/Keras	Deep Learning Models
Pandas, NumPy	Data Handling & Preprocessing
CSS	Frontend Styling

---

🚀 How It Works

1️⃣ Data Preprocessing – Cleans and prepares user-uploaded images.
2️⃣ Model Prediction – Uses a CNN model to classify defects (e.g., "hole," "oil spot").
3️⃣ Web Interface:

• Upload images for prediction.
• View results dynamically.
• Log in for personalized access.
  4️⃣ Feedback and Contact Forms – Allows users to provide feedback and inquiries.

---

⚡ Getting Started

🔧 Prerequisites

• Python 3.7+
• Flask
• TensorFlow/Keras
• SQLite

📌 Installation

# Clone the repository
git clone https://github.com/NakulLimbani/Fabric_Textile_Cloth_Defect_Detection_and_Classification.git

# Navigate to the project directory
cd Fabric_Textile_Cloth_Defect_Detection_and_Classification/Cloth_Defects_Detection

# Install dependencies
pip install -r requirements.txt

# Run the Flask app
python app.py

🌐 Access the Website

Open your browser and visit http://127.0.0.1:5000/ to access the application.

---

📊 Results & Performance

• Model Accuracy:
  • Logistic Regression: 90%+
  • CNN Model: 95%+
• Prediction Categories:
  • Non-Defective, Hole, Oil Spot, Thread Error, Objects

---

📋 Routes

Route	Description
/	Home Page
/login	User Login
/signup	User Registration
/predict	Image Upload & Defect Prediction
/about	About the Project
/contact	Contact Form
/feedback	Feedback Form

---

📜 License

This project is licensed under the MIT License.

---