arXiv:2512.04464v1 Announce Type: cross 
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.

تم إجراء دراسة مقارنة حول تصنيف العملات الذهبية من نوع سانت غودنس دابل إيجل تلقائيًا، متحديةً الاعتقاد الشائع بأن التعلم العميق دائمًا ما يتفوق على التقنيات القديمة. اختبرت الدراسة شبكة عصبية صناعية (ANN) مقابل شبكة عصبية تلافيفية هجينة (CNN) وآلة دعم المتجهات (SVM)، كاشفةً أن ANN حققت 86% من المطابقات الدقيقة و98% مع هامش 3 درجات، بينما كانت نتائج CNN وSVM ضعيفة، حيث حققت 31% و30% من المطابقات الدقيقة، على التوالي.

Se ha realizado un estudio comparativo sobre la clasificación automatizada de monedas de oro Saint-Gaudens Double Eagle, desafiando la creencia de que el aprendizaje profundo siempre es superior a las técnicas más antiguas. El estudio probó una Red Neuronal Artificial (ANN) frente a una Red Neuronal Convolucional (CNN) híbrida y una Máquina de Vectores de Soporte (SVM), revelando que la ANN logró un 86% de coincidencias exactas y un 98% con un margen de 3 grados, mientras que la CNN y la SVM tuvieron un rendimiento deficiente con solo un 31% y un 30% de coincidencias exactas, respectivamente.

Une étude comparative a été réalisée sur le classement automatisé des pièces d'or Saint-Gaudens Double Eagle, remettant en question la notion selon laquelle l'apprentissage profond est supérieur aux méthodes traditionnelles. L'étude a testé un réseau de neurones artificiels (ANN) contre un réseau de neurones convolutifs hybride (CNN) et une machine à vecteurs de support (SVM), révélant que l'ANN a atteint 86 % de correspondances exactes et 98 % avec une tolérance de 3 grades, tandis que le CNN et la SVM ont obtenu des performances médiocres avec seulement 31 % et 30 % de correspondances exacte…

A comparative study has been conducted on automated grading of Saint-Gaudens Double Eagle gold coins, challenging the notion that deep learning is superior to traditional methods. The study tested an Artificial Neural Network (ANN) against a hybrid Convolutional Neural Network (CNN) and a Support Vector Machine (SVM), revealing that the ANN achieved 86% exact matches and 98% with a 3-grade leeway, while the CNN and SVM performed poorly with only 31% and 30% exact hits, respectively.

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

arXiv:2512.05021v1 Announce Type: cross 
Abstract: Handwritten Text Recognition remains challenging due to the limited data, high writing style variance, and scripts with complex diacritics. Existing approaches, though partially address these issues, often struggle to generalize without massive synthetic data. To address these challenges, we propose HTR-ConvText, a model designed to capture fine-grained, stroke-level local features while preserving global contextual dependencies. In the feature extraction stage, we integrate a residual Convolutional Neural Network backbone with a MobileViT with Positional Encoding block. This enables the model to both capture structural patterns and learn subtle writing details. We then introduce the ConvText encoder, a hybrid architecture combining global context and local features within a hierarchical structure that reduces sequence length for improved efficiency. Additionally, an auxiliary module injects textual context to mitigate the weakness of Connectionist Temporal Classification. Evaluations on IAM, READ2016, LAM and HANDS-VNOnDB demonstrate that our approach achieves improved performance and better generalization compared to existing methods, especially in scenarios with limited training samples and high handwriting diversity.

تم تقديم HTR-ConvText كنموذج جديد يهدف إلى تحسين التعرف على النصوص المكتوبة بخط اليد من خلال التقاط الميزات المحلية على مستوى الخطوط والاعتماد على السياقات العالمية بشكل فعال. يدمج هذا النموذج شبكة عصبية تلافيفية متبقية مع بنية MobileViT، مما يعزز القدرة على التعرف على أنماط الكتابة المعقدة والنصوص ذات التشكيلات.

HTR-ConvText se ha presentado como un nuevo modelo diseñado para mejorar el reconocimiento de texto manuscrito al capturar de manera efectiva tanto características locales a nivel de trazo como dependencias contextuales globales. Este modelo integra una red neuronal convolucional residual con una arquitectura MobileViT, mejorando la capacidad para reconocer estilos de escritura complejos y scripts con diacríticos.

HTR-ConvText a été présenté comme un nouveau modèle visant à améliorer la reconnaissance de l'écriture manuscrite en capturant efficacement à la fois les caractéristiques locales au niveau des traits et les dépendances contextuelles globales. Ce modèle intègre un réseau de neurones convolutifs résiduels avec une architecture MobileViT, améliorant la capacité à reconnaître des styles d'écriture complexes et des scripts avec des diacritiques.

HTR-ConvText has been introduced as a novel model aimed at improving handwritten text recognition by effectively capturing both local stroke-level features and global contextual dependencies. This model integrates a residual Convolutional Neural Network with a MobileViT architecture, enhancing the ability to recognize complex writing styles and scripts with diacritics.

HTR-ConvText: Leveraging Convolution and Textual Information for Handwritten Text Recognition

arXiv:2506.14987v3 Announce Type: replace-cross 
Abstract: Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a CNN-based dynamic priority prediction mechanism for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach uses a Convolutional Neural Network and graph coloring to adaptively assign link priorities based on real-time traffic, transmission opportunities, and network conditions. Assuming that first training phase is performed offline, our approach introduced minimal overhead, while enabling more efficient resource allocation, boosting network capacity, SINR, and schedulability. Simulation results show SINR gains of up to 113\%, 94\%, and 49\% over LDP across three network configurations, highlighting its effectiveness for complex URLLC scenarios.

تم تقديم نهج جديد للجدولة في الاتصالات فائقة الموثوقية ومنخفضة الكمون (URLLC) من خلال تحسين خوارزمية تقسيم المواعيد المحلي (LDP) باستخدام آلية توقع أولوية ديناميكية تعتمد على الشبكات العصبية التلافيفية (CNN). تهدف هذه الابتكارات إلى تحسين تنسيق التداخل في الشبكات المعقدة متعددة الخلايا والقنوات من خلال تخصيص أولويات الروابط بشكل تكيفي بناءً على الظروف في الوقت الحقيقي.

Se ha introducido un nuevo enfoque para la programación en comunicaciones ultra confiables y de baja latencia (URLLC), mejorando el algoritmo de Local Deadline Partition (LDP) con un mecanismo de predicción de prioridad dinámica basado en CNN. Esta innovación tiene como objetivo mejorar la coordinación de interferencias en redes complejas de múltiples celdas y múltiples canales al asignar de manera adaptativa prioridades de enlace según las condiciones en tiempo real.

Une nouvelle approche de planification dans les communications ultra-fiables et à faible latence (URLLC) a été introduite, améliorant l'algorithme de Local Deadline Partition (LDP) avec un mécanisme de prédiction de priorité dynamique basé sur CNN. Cette innovation vise à améliorer la coordination des interférences dans des réseaux complexes multi-cellules et multi-canaux en attribuant de manière adaptative des priorités de lien en fonction des conditions en temps réel.

A new approach to scheduling in ultra-reliable, low-latency communications (URLLC) has been introduced, enhancing the Local Deadline Partition (LDP) algorithm with a CNN-based dynamic priority prediction mechanism. This innovation aims to improve interference coordination in complex multi-cell, multi-channel networks by adaptively assigning link priorities based on real-time conditions.

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

Was this article worth reading? Share it

WasItAI

CoGrader

Attentive AI