Feature Engineering vs. Deep Learning for Automated Coin Grading: A Comparative Study on Saint-Gaudens Double Eagles

TL;DR

This study compares feature-based neural networks and deep learning models for automated coin grading, finding that feature engineering with traditional models outperforms CNNs in small, imbalanced datasets.

Contribution

It demonstrates that handcrafted feature extraction combined with neural networks can outperform deep learning models in niche, data-limited coin grading tasks.

Findings

Feature-based ANN achieved 86% exact match accuracy.

CNN and SVM performed poorly with around 30% accuracy.

Real coin-expert knowledge in features outperforms deep learning in small datasets.

Abstract

We challenge the common belief that deep learning always trumps older techniques, using the example of grading Saint-Gaudens Double Eagle gold coins automatically. In our work, we put a feature-based Artificial Neural Network built around 192 custom features pulled from Sobel edge detection and HSV color analysis up against a hybrid Convolutional Neural Network that blends in EfficientNetV2, plus a straightforward Support Vector Machine as the control. Testing 1,785 coins graded by experts, the ANN nailed 86% exact matches and hit 98% when allowing a 3-grade leeway. On the flip side, CNN and SVM mostly just guessed the most common grade, scraping by with 31% and 30% exact hits. Sure, the CNN looked good on broader tolerance metrics, but that is because of some averaging trick in regression that hides how it totally flops at picking out specific grades. All told, when you are stuck with under 2,000 examples and lopsided classes, baking in real coin-expert knowledge through feature design beats out those inscrutable, all-in-one deep learning setups. This rings true for other niche quality checks where data's thin and know-how matters more than raw compute.