# A Sobel-Gradient MLP Baseline for Handwritten Character Recognition

arXiv: https://arxiv.org/abs/2508.11902 · HTML: https://mlsanity.com/paper/2508.11902/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 23 references that are in the map.
- First posted on arXiv 16 Aug 2025.

## Builds on (most cited first, 4 of 4)

- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [EMNIST: an extension of MNIST to handwritten letters](https://mlsanity.com/paper/1702.05373/) (2017)
- [An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation](https://mlsanity.com/paper/2508.11803/) (2025)

## Built on by (most cited first, 3 of 3)

- [Significance-Gain Pair Encoding for LLMs: A Statistical Alternative to Frequency-Based Subword Merging](https://mlsanity.com/paper/2603.19261/) (2026)
- [StepCache: Step-Level Reuse with Lightweight Verification and Selective Patching for LLM Serving](https://mlsanity.com/paper/2603.28795/) (2026)
- [MDL-Calibrated Significance-Gain Pair Encoding: Replication-Aware Automatic Stopping for Subword Tokenization](https://mlsanity.com/paper/2609.31705/) (2026)

## Abstract (arXiv)

This study examines how much handwritten-character information is retained by a deliberately simple first-order edge representation. Instead of learning spatial filters, each input image is transformed by the fixed Sobel-Feldman operator into signed horizontal and vertical derivative maps, which are independently normalized, flattened, and classified by a multilayer perceptron (MLP). The resulting model therefore separates fixed edge extraction from learned classification and provides a controlled baseline for evaluating the sufficiency of first-order image gradients. In the executed experiments, the Sobel-gradient MLP achieves 98.54 percent test accuracy on MNIST and 92.50 percent on the TensorFlow Datasets (TFDS) EMNIST Letters configuration. Macro F1 scores are 0.9853 and 0.9265, respectively. One-vs-rest ROC analysis further yields micro/macro AUC values of 0.9998/0.9998 on MNIST and 0.9987/0.9982 on EMNIST Letters. Confusion-matrix analysis shows that the remaining errors are concentrated among geometrically similar classes, especially 3/8 and 4/9 for MNIST and I/L and G/Q for EMNIST Letters. These results show that fixed first-order gradients preserve substantial class-discriminative structure, while also revealing the specific ambiguities that remain when recognition is driven by edge geometry alone.