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.
Abstract (translated)
我们挑战了深度学习总是优于传统技术的普遍观点，通过自动评估圣高登斯双鹰金元硬币等级的例子来说明这一点。在我们的研究中，我们将一种基于192个自定义特征构建的功能型人工神经网络（ANN）与融合EfficientNetV2的混合卷积神经网络（CNN），以及作为对照组的支持向量机（SVM）进行了对比测试。这192个自定义特征是从索贝尔边缘检测和HSV颜色分析中提取出来的。我们用专家评估过的1,785枚硬币进行测试，结果发现ANN在完全匹配的情况下达到了86%的准确率，在允许±3等级偏差的情况下则达到98%的准确性。另一方面，CNN和SVM大多数时候只是猜测最常见的等级，精确匹配的准确率分别为31%和30%。虽然CNN在更宽松的标准下表现良好，但这主要是因为它在回归任务中使用了一些平均技巧来掩盖其在识别特定等级时完全失败的事实。 总的来说，在样本数量不足2,000且分类不均衡的情况下，通过设计特有硬币专家知识的功能型人工神经网络优于那些难以理解的一体化深度学习模型。这一结论同样适用于其他数据稀疏、专业知识比原始计算能力更重要的细分质量检查领域。
URL
https://arxiv.org/abs/2512.04464
