CNN for Image Classification

The project includes collaborative efforts in applying pattern recognition and image classification techniques. The primary focus is on the MNIST dataset, with attempts that explore digit classification and neural network optimizations.

My Contribution

I was the project lead in this Pattern Recognition project. My work included model training and building, hyperparameter optimization, and performance evaluation in both the custom Convolutional Neural Network and DenseNet architecture, achieving significant improvements in accuracy and model convergence.

Project Overview

Part 1: Custom CNN for Image Classification

This project involves the design and implementation of a custom Convolutional Neural Network (CNN) to classify handwritten digits from the MNIST dataset.

Repository: Custom CNN Implementation

Key Features:

• Custom CNN architecture built using PyTorch.
• Dataset split into training, validation, and testing sets.
• Comprehensive evaluation using metrics like accuracy, confusion matrix, precision, and recall.

Training and Validation loss curves:

Part 2: State-of-the-Art CNN Implementations

Each team member implemented and fine-tuned a pre-trained CNN architecture to compare its performance with the custom model:

DenseNet: Fine-tuned for accuracy improvements and faster convergence.

ResNet: Utilized residual connections for handling deeper layers.

GoogLeNet: Fine-tuned for complex image classification tasks.

VGG: Optimized for feature extraction.

Results

Repositories

• DenseNet Implementation
• ResNet Implementation
• GoogLeNet Implementation
• VGG Implementation

Pending update on overall results.

This project provides a comprehensive foundation in CNN-based image classification, demonstrating both theoretical understanding and practical implementation skills in deep learning and computer vision.

For more details and to explore the implementation, visit the GitHub Organization.