An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Nouri, Azam
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909868202393600
author Nouri, Azam
author_facet Nouri, Azam
contents This study investigates whether second-order geometric cues - planar curvature magnitude, curvature sign, and gradient orientation - are sufficient on their own to drive a multilayer perceptron (MLP) classifier for handwritten character recognition (HCR), offering an alternative to convolutional neural networks (CNNs). Using these three handcrafted feature maps as inputs, our curvature-orientation MLP achieves 97 percent accuracy on MNIST digits and 89 percent on EMNIST letters. These results underscore the discriminative power of curvature-based representations for handwritten character images and demonstrate that the advantages of deep learning can be realized even with interpretable, hand-engineered features.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11803
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
Nouri, Azam
Computer Vision and Pattern Recognition
Machine Learning
This study investigates whether second-order geometric cues - planar curvature magnitude, curvature sign, and gradient orientation - are sufficient on their own to drive a multilayer perceptron (MLP) classifier for handwritten character recognition (HCR), offering an alternative to convolutional neural networks (CNNs). Using these three handcrafted feature maps as inputs, our curvature-orientation MLP achieves 97 percent accuracy on MNIST digits and 89 percent on EMNIST letters. These results underscore the discriminative power of curvature-based representations for handwritten character images and demonstrate that the advantages of deep learning can be realized even with interpretable, hand-engineered features.
title An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2508.11803