Abstract
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.
Abstract (translated)
这项研究探讨了第二阶几何线索——平面曲率大小、曲率符号和梯度方向——是否足以驱动多层感知器（MLP）分类器来进行手写字符识别（HCR），以此为卷积神经网络（CNNs）提供一种替代方案。使用这三个手工设计的特征图作为输入，我们的曲率-方向MLP在MNIST数字数据集上达到了97%的准确率，在EMNIST字母数据集上则达到89%的准确率。这些结果强调了基于曲率表示对手写字符图像判别能力的重要性，并表明即使使用可解释的手工设计特征，也能实现深度学习的优势。
URL
https://arxiv.org/abs/2508.11803
