Image Blur vs. Sharp Classification Using Traditional Neural Networks

This project focuses on building a machine learning model to classify images into two categories: blurred and sharp images. The goal is to analyze image quality using traditional neural network techniques and extract meaningful features

The workflow includes image preprocessing, feature extraction, and training a neural network model for binary classification. The data

The model learns patterns related to edge strength, texture, and pixel intensity variations to differentiate between blurred and sharp images effectively.

Key Tasks:

Image pre

Feature extracti

Building a traditi

Training and evaluation for binary classification

Performance analysis using accuracy metrics

Tools & Technologies:

Python, NumPy, TensorFlow / Keras (or PyTorch if you used it), OpenCV, Machine Learning

Outcome:

A trained classification model capable of distinguishing between blurred and sharp images, demonstrating basic computer vision and neural network concepts.