用几何特征训练MLP，手写数字识别准确率达97%。
An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
- 用曲率大小、符号和梯度方向三类手工特征输入MLP
- MNIST上达97%准确率，EMNIST字母达89%
- 无需CNN也能实现深度学习效果，且特征可解释
本研究探讨了二阶几何线索——平面曲率幅度、曲率符号和梯度方向——是否足以驱动多层感知机（MLP）分类器完成手写字符识别（HCR），作为卷积神经网络（CNN）的替代方案。将这三个手工特征图作为输入，基于曲率与方向的MLP在MNIST数字上达到97%的准确率，在EMNIST字母上达到89%。结果表明，基于曲率的表征具有强大的判别能力，即使使用可解释的手工特征，也能实现深度学习的优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。