MNIST Dataset Classification Utilizing k-NN Classifier with Modified Sliding-window Metric

TL;DR

This paper improves MNIST digit classification by enhancing the k-NN algorithm with a sliding-window-based distance metric, leading to better accuracy by handling spatial misalignments.

Contribution

The paper introduces a modified distance metric using a sliding window technique for k-NN, improving classification accuracy on MNIST.

Findings

Significant accuracy improvement with the sliding window method

Better handling of spatial misalignments in digit images

Enhanced k-NN performance over standard Euclidean distance

Abstract

The MNIST dataset of the handwritten digits is known as one of the commonly used datasets for machine learning and computer vision research. We aim to study a widely applicable classification problem and apply a simple yet efficient K-nearest neighbor classifier with an enhanced heuristic. We evaluate the performance of the K-nearest neighbor classification algorithm on the MNIST dataset where the $L2$ Euclidean distance metric is compared to a modified distance metric which utilizes the sliding window technique in order to avoid performance degradation due to slight spatial misalignments. The accuracy metric and confusion matrices are used as the performance indicators to compare the performance of the baseline algorithm versus the enhanced sliding window method and results show significant improvement using this proposed method.