An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
This work addresses handwriting recognition for digit and letter classification, offering an interpretable alternative to CNNs, though it is incremental in scope.
The study tackled handwritten character recognition by using planar curvature and gradient orientation as inputs to an MLP, achieving 97% accuracy on MNIST digits and 89% on EMNIST letters.
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.