Handwriting
-
ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents
2025-09-16 11:17:03Silvia Zottin, Axel De Nardin, Giuseppe Branca, Claudio Piciarelli, Gian Luca ForestiAbstract
Text line segmentation is a critical step in handwritten document image analysis. Segmenting text lines in historical handwritten documents, however, presents unique challenges due to irregular handwriting, faded ink, and complex layouts with overlapping lines and non-linear text flow. Furthermore, the scarcity of large annotated datasets renders fully supervised learning approaches impractical for such materials. To address these challenges, we introduce the Few-Shot Text Line Segmentation of Ancient Handwritten Documents (FEST) Competition. Participants are tasked with developing systems capable of segmenting text lines in U-DIADS-TL dataset, using only three annotated images per manuscript for training. The competition dataset features a diverse collection of ancient manuscripts exhibiting a wide range of layouts, degradation levels, and non-standard formatting, closely reflecting real-world conditions. By emphasizing few-shot learning, FEST competition aims to promote the development of robust and adaptable methods that can be employed by humanities scholars with minimal manual annotation effort, thus fostering broader adoption of automated document analysis tools in historical research.
Abstract (translated)
文本行分割是手写文档图像分析中的关键步骤。然而，在历史手写文档中进行文本行分割面临着一些独特的挑战，例如不规则的笔迹、褪色的墨水以及包含重叠线条和非线性文本流动的复杂布局。此外，由于大型标注数据集的稀缺，完全监督的学习方法在这种材料上显得不太实际。为了解决这些问题，我们推出了《古代手写文档文本行分割少样本学习竞赛》（FEST）。参赛者需要开发能够在使用U-DIADS-TL数据集中仅有的三张标记图像进行训练的情况下，对文本行进行分割的系统。 该竞赛的数据集包含了一系列具有不同布局、退化程度和非标准格式的古代手稿，这与真实世界的情况非常接近。通过强调少样本学习，FEST竞赛旨在促进开发出稳健且适应性强的方法，这些方法可以在需要最少人工标注努力的情况下被人文学者采用，并推动自动化文档分析工具在历史研究中的广泛应用。
URL
https://arxiv.org/abs/2509.12965
PDF
-
Well-Conditioned Polynomial Representations for Mathematical Handwriting Recognition
2025-09-13 14:31:18Robert M. Corless, Deepak Singh Kalhan, Stephen M. WattAbstract
Previous work has made use of a parameterized plane curve polynomial representation for mathematical handwriting, with the polynomials represented in a Legendre or Legendre-Sobolev graded basis. This provides a compact geometric representation for the digital ink. Preliminary results have also been shown for Chebyshev and Chebyshev-Sobolev bases. This article explores the trade-offs between basis choice and polynomial degree to achieve accurate modeling with a low computational cost. To do this, we consider the condition number for polynomial evaluation in these bases and bound how the various inner products give norms for the variations between symbols.
Abstract (translated)
先前的工作利用了参数化平面曲线多项式表示法来描述数学手写，其中多项式用Legendre或Legendre-Sobolev分层基表示。这种方法为数字墨水提供了一种紧凑的几何表示方式。初步结果显示，Chebyshev和Chebyshev-Sobolev基底也适用。本文探讨了在选择不同基底和多项式次数之间进行权衡，以实现精确建模并降低计算成本的方法。为此，我们考虑了这些基底中多项式评估的条件数，并界定了各种内积如何给出符号间差异的范数。
URL
https://arxiv.org/abs/2509.10815
PDF
-
KoopMotion: Learning Almost Divergence Free Koopman Flow Fields for Motion Planning
2025-09-11 00:42:01Alice Kate Li, Thales C Silva, Victoria Edwards, Vijay Kumar, M. Ani HsiehAbstract
In this work, we propose a novel flow field-based motion planning method that drives a robot from any initial state to a desired reference trajectory such that it converges to the trajectory's end point. Despite demonstrated efficacy in using Koopman operator theory for modeling dynamical systems, Koopman does not inherently enforce convergence to desired trajectories nor to specified goals -- a requirement when learning from demonstrations (LfD). We present KoopMotion which represents motion flow fields as dynamical systems, parameterized by Koopman Operators to mimic desired trajectories, and leverages the divergence properties of the learnt flow fields to obtain smooth motion fields that converge to a desired reference trajectory when a robot is placed away from the desired trajectory, and tracks the trajectory until the end point. To demonstrate the effectiveness of our approach, we show evaluations of KoopMotion on the LASA human handwriting dataset and a 3D manipulator end-effector trajectory dataset, including spectral analysis. We also perform experiments on a physical robot, verifying KoopMotion on a miniature autonomous surface vehicle operating in a non-static fluid flow environment. Our approach is highly sample efficient in both space and time, requiring only 3\% of the LASA dataset to generate dense motion plans. Additionally, KoopMotion provides a significant improvement over baselines when comparing metrics that measure spatial and temporal dynamics modeling efficacy.
Abstract (translated)
在这项工作中，我们提出了一种基于流场的运动规划方法，该方法能够引导机器人从任意初始状态到达期望参考轨迹，并确保最终收敛到该轨迹的终点。尽管Koopman算子理论在建模动力系统方面已经显示出良好的效果，但Koopman本身并不能自然地强制使系统向期望的轨迹或指定的目标收敛——这是从演示学习（LfD）时所需的关键特性。我们提出了名为KoopMotion的方法，它将运动流场表示为动态系统，并利用Koopman算子进行参数化以模仿所需的轨迹。此外，该方法通过利用所学流场的散度属性来获得平滑的运动场，在机器人远离期望轨迹时能够收敛到期望参考轨迹，并在到达终点之前始终跟踪此轨迹。 为了展示我们方法的有效性，我们在LASA人类手写数据集和一个3D机械臂末端执行器轨迹数据集上对KoopMotion进行了评估，包括频谱分析。此外，还在实际机器人上进行实验，在非静态流体环境中验证了KoopMotion在微型自主水面车辆上的应用。 我们的方法在空间和时间样本效率方面都非常高，仅需使用LASA数据集的3%就可以生成密集的运动计划。当比较用于衡量时空动力学建模效果的指标时，KoopMotion也显著优于基线模型。
URL
https://arxiv.org/abs/2509.09074
PDF
-
A comprehensive Persian offline handwritten database for investigating the effects of heritability and family relationships on handwriting
2025-09-03 17:47:23Abbas Zohrevand, Javad Sadri, Zahra ImaniAbstract
This paper introduces a comprehensive database for research and investigation on the effects of inheritance on handwriting. A database has been created that can be used to answer questions such as: Is there a genetic component to handwriting? Is handwriting inherited? Do family relationships affect handwriting? Varieties of samples of handwritten components such as: digits, letters, shapes and free paragraphs of 210 families including (grandparents, parents, uncles, aunts, siblings, cousins, nephews and nieces) have been collected using specially designed forms, and family relationships of all writers are captured. To the best of our knowledge, no such database is presently available. Based on comparisons and investigation of features of handwritings of family members, similarities among their features and writing styles are detected. Our database is freely available to the pattern recognition community and hope it will pave the way for investigations on the effects of inheritance and family relationships on handwritings.
Abstract (translated)
本文介绍了一个全面的数据库，用于研究和调查继承对书写风格的影响。该数据库可以用来回答诸如以下问题：书写中是否存在遗传因素？书写是否可以通过遗传传递？家庭关系会影响书写的特征吗？ 为了构建这个数据库，我们收集了210个家庭（包括祖父母、父母、叔伯姑姨、兄弟姐妹、堂表兄弟姐妹、侄子和侄女）的各种手写样本。这些样本涵盖了数字、字母、形状以及自由段落等形式，并通过专门设计的表格进行采集。此外，所有书写者的家族关系也被记录在案。 据我们所知，目前没有类似这样的数据库存在。通过对家庭成员之间手写字迹特征及书写风格的比较和研究，可以检测出他们之间的相似性。我们的数据库对模式识别社区免费开放，并希望它能够为探究遗传因素及家庭关系对手写的影响开辟新的道路。
URL
https://arxiv.org/abs/2509.03510
PDF
-
A Stroke-Level Large-Scale Database of Chinese Character Handwriting and the OpenHandWrite_Toolbox for Handwriting Research
2025-09-01 07:19:37Zebo Xu, Shaoyun Yu, Mark Torrance, Guido Nottbusch, Nan Zhao, Zhenguang CaiAbstract
Understanding what linguistic components (e.g., phonological, semantic, and orthographic systems) modulate Chinese handwriting at the character, radical, and stroke levels remains an important yet understudied topic. Additionally, there is a lack of comprehensive tools for capturing and batch-processing fine-grained handwriting data. To address these issues, we constructed a large-scale handwriting database in which 42 Chinese speakers for each handwriting 1200 characters in a handwriting-to-dictation task. Additionally, we enhanced the existing handwriting package and provided comprehensive documentation for the upgraded OpenHandWrite_Toolbox, which can easily modify the experimental design, capture the stroke-level handwriting trajectory, and batch-process handwriting measurements (e.g., latency, duration, and pen-pressure). In analysing our large-scale database, multiple regression results show that orthographic predictors impact handwriting preparation and execution across character, radical, and stroke levels. Phonological factors also influence execution at all three levels. Importantly, these lexical effects demonstrate hierarchical attenuation - they were most pronounced at the character level, followed by the radical, and were weakest at the stroke levels. These findings demonstrate that handwriting preparation and execution at the radical and stroke levels are closely intertwined with linguistic components. This database and toolbox offer valuable resources for future psycholinguistic and neurolinguistic research on the handwriting of characters and sub-characters across different languages.
Abstract (translated)
理解哪些语言成分（例如，音位、语义和正字法系统）在字符、偏旁和笔画级别上调节中文手写仍然是一个重要的但研究不足的话题。此外，缺乏捕捉和批量处理精细手写数据的全面工具。为解决这些问题，我们构建了一个大规模的手写数据库，在该数据库中42名中国参与者每人完成了1200个汉字的手写至听写任务。另外，我们改进了现有的手写软件包，并提供了详细的文档来升级OpenHandWrite_Toolbox，这个升级后的工具有助于轻松修改实验设计、捕捉笔画级手写轨迹以及批量处理手写测量（例如延迟时间、持续时间和笔压）。在分析我们的大规模数据库时，多重回归结果显示正字法预测因子对手写准备和执行在字符、偏旁和笔画级别上均有影响。音位因素也对所有三个级别的执行有影响。尤为重要的是，这些词汇效应表现出层次递减——它们在字符层面上最为明显，在偏旁层面上次之，在笔画层面上最弱。这些发现表明手写准备和执行在偏旁和笔划层面与语言成分密切相关。该数据库和工具包为未来跨不同语言的汉字及字部件的心理语言学和神经语言学研究提供了宝贵的资源。
URL
https://arxiv.org/abs/2509.05335
PDF
-
FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator
2025-08-28 17:44:52Huynh Tong Dang Khoa, Dang Hoai Nam, Vo Nguyen Le DuyAbstract
Labeled handwriting data is often scarce, limiting the effectiveness of recognition systems that require diverse, style-consistent training samples. Handwriting synthesis offers a promising solution by generating artificial data to augment training. However, current methods face two major limitations. First, most are built on conventional convolutional architectures, which struggle to model long-range dependencies and complex stroke patterns. Second, they largely ignore the crucial role of frequency information, which is essential for capturing fine-grained stylistic and structural details in handwriting. To address these challenges, we propose FW-GAN, a one-shot handwriting synthesis framework that generates realistic, writer-consistent text from a single example. Our generator integrates a phase-aware Wave-MLP to better capture spatial relationships while preserving subtle stylistic cues. We further introduce a frequency-guided discriminator that leverages high-frequency components to enhance the authenticity detection of generated samples. Additionally, we introduce a novel Frequency Distribution Loss that aligns the frequency characteristics of synthetic and real handwriting, thereby enhancing visual fidelity. Experiments on Vietnamese and English handwriting datasets demonstrate that FW-GAN generates high-quality, style-consistent handwriting, making it a valuable tool for augmenting data in low-resource handwriting recognition (HTR) pipelines. Official implementation is available at this https URL
Abstract (translated)
标注的手写数据通常稀缺，这限制了需要多样化且风格一致的训练样本的识别系统的有效性。手写合成通过生成人工数据来扩充训练集，提供了一种有前景的解决方案。然而，当前的方法面临两个主要局限：首先，大多数方法建立在传统的卷积架构之上，这种架构难以建模长距离依赖关系和复杂的笔画模式；其次，它们很大程度上忽略了频域信息的关键作用，而这一信息对于捕捉手写中细微的风格和结构细节至关重要。 为了解决这些挑战，我们提出了FW-GAN（Frequency-aware Wave-MLP Generator），这是一种单样本的手写合成框架。该生成器集成了一个感知相位的Wave-MLP模块，以更好地捕获空间关系并保持微妙的风格线索。此外，我们引入了一个基于频域指导的判别器，利用高频成分来提高对生成样本真实性的检测能力。同时，还提出了一种新颖的频率分布损失函数，使合成的手写与真实的书写在频域特征上更加一致，从而提升视觉保真度。 实验表明，在越南语和英语手写数据集上的测试中，FW-GAN能够生成高质量且风格一致的手写样本，这使其成为低资源环境下扩充数据以提高手写识别（HTR）效果的重要工具。官方实现可在以下链接获取：[请在此处提供具体网址]
URL
https://arxiv.org/abs/2508.21040
PDF
-
TrInk: Ink Generation with Transformer Network
2025-08-28 01:44:15Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie LiuAbstract
In this paper, we propose TrInk, a Transformer-based model for ink generation, which effectively captures global dependencies. To better facilitate the alignment between the input text and generated stroke points, we introduce scaled positional embeddings and a Gaussian memory mask in the cross-attention module. Additionally, we design both subjective and objective evaluation pipelines to comprehensively assess the legibility and style consistency of the generated handwriting. Experiments demonstrate that our Transformer-based model achieves a 35.56\% reduction in character error rate (CER) and an 29.66% reduction in word error rate (WER) on the IAM-OnDB dataset compared to previous methods. We provide an demo page with handwriting samples from TrInk and baseline models at: this https URL
Abstract (translated)
在这篇论文中，我们提出了TrInk，这是一种基于Transformer的墨迹生成模型，能够有效捕捉全局依赖关系。为了更好地促进输入文本和生成笔画点之间的对齐，我们在跨注意力模块中引入了缩放位置嵌入和高斯记忆掩码。此外，我们还设计了主观和客观评估管道，以全面评估所生成手写体的可读性和风格一致性。实验表明，在IAM-OnDB数据集上，我们的基于Transformer的模型相比先前的方法将字符错误率（CER）降低了35.56%，将单词错误率（WER）降低了29.66%。我们提供了一个演示页面，其中包含TrInk和基线模型的手写样本：[此处应为URL链接]
URL
https://arxiv.org/abs/2508.21098
PDF
-
Enhanced Hybrid Technique for Efficient Digitization of Handwritten Marksheets
2025-08-22 10:57:27Junaid Ahmed Sifat, Abir Chowdhury, Hasnat Md. Imtiaz, Md. Irtiza Hossain, Md. Imran Bin AzadAbstract
The digitization of handwritten marksheets presents huge challenges due to the different styles of handwriting and complex table structures in such documents like marksheets. This work introduces a hybrid method that integrates OpenCV for table detection and PaddleOCR for recognizing sequential handwritten text. The image processing capabilities of OpenCV efficiently detects rows and columns which enable computationally lightweight and accurate table detection. Additionally, YOLOv8 and Modified YOLOv8 are implemented for handwritten text recognition within the detected table structures alongside PaddleOCR which further enhance the system's versatility. The proposed model achieves high accuracy on our custom dataset which is designed to represent different and diverse handwriting styles and complex table layouts. Experimental results demonstrate that YOLOv8 Modified achieves an accuracy of 92.72 percent, outperforming PaddleOCR 91.37 percent and the YOLOv8 model 88.91 percent. This efficiency reduces the necessity for manual work which makes this a practical and fast solution for digitizing academic as well as administrative documents. This research serves the field of document automation, particularly handwritten document understanding, by providing operational and reliable methods to scale, enhance, and integrate the technologies involved.
Abstract (translated)
手写成绩单的数字化面临巨大挑战，因为不同人的书写风格和此类文档（如成绩单）中复杂的表格结构。本工作提出了一种混合方法，结合使用OpenCV进行表格检测以及PaddleOCR识别连续的手写文本。OpenCV的图像处理能力能够有效检测行与列，从而使表格检测更加轻量级且准确。此外，还实施了YOLOv8和改良版YOLOv8，在检测到的表格结构中与PaddleOCR一起用于手写文本识别，进一步增强了系统的灵活性。 所提出的模型在我们定制的数据集上实现了高精度，该数据集旨在代表各种不同的书写风格和复杂的表格布局。实验结果表明，改良版YOLOv8达到了92.72%的准确率，优于PaddleOCR（91.37%）和原始YOLOv8模型（88.91%）。这种效率降低了手动操作的需求，使得该方法成为数字化学术及行政文档的一种实际且快速的解决方案。 这项研究为文档自动化领域，特别是手写文档的理解提供了可操作且可靠的方法，有助于扩展、增强并整合相关技术。
URL
https://arxiv.org/abs/2508.16295
PDF
-
An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
Abstract
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.
Abstract (translated)
这项研究探讨了第二阶几何线索——平面曲率大小、曲率符号和梯度方向——是否足以驱动多层感知器（MLP）分类器来进行手写字符识别（HCR），以此为卷积神经网络（CNNs）提供一种替代方案。使用这三个手工设计的特征图作为输入，我们的曲率-方向MLP在MNIST数字数据集上达到了97%的准确率，在EMNIST字母数据集上则达到89%的准确率。这些结果强调了基于曲率表示对手写字符图像判别能力的重要性，并表明即使使用可解释的手工设计特征，也能实现深度学习的优势。
URL
https://arxiv.org/abs/2508.11803
PDF
-
Handwritten Text Recognition of Historical Manuscripts Using Transformer-Based Models
Abstract
Historical handwritten text recognition (HTR) is essential for unlocking the cultural and scholarly value of archival documents, yet digitization is often hindered by scarce transcriptions, linguistic variation, and highly diverse handwriting styles. In this study, we apply TrOCR, a state-of-the-art transformer-based HTR model, to 16th-century Latin manuscripts authored by Rudolf Gwalther. We investigate targeted image preprocessing and a broad suite of data augmentation techniques, introducing four novel augmentation methods designed specifically for historical handwriting characteristics. We also evaluate ensemble learning approaches to leverage the complementary strengths of augmentation-trained models. On the Gwalther dataset, our best single-model augmentation (Elastic) achieves a Character Error Rate (CER) of 1.86, while a top-5 voting ensemble achieves a CER of 1.60 - representing a 50% relative improvement over the best reported TrOCR_BASE result and a 42% improvement over the previous state of the art. These results highlight the impact of domain-specific augmentations and ensemble strategies in advancing HTR performance for historical manuscripts.
Abstract (translated)
历史手写文本识别（HTR）对于释放档案文献的文化和学术价值至关重要，然而由于缺乏转录、语言差异以及书写风格的高度多样性，数字化工作常常受到阻碍。在这项研究中，我们应用了TrOCR这一基于Transformer的最先进的HTR模型，对16世纪鲁道夫·格瓦尔特（Rudolf Gwalther）撰写的拉丁文手稿进行了处理。我们在图像预处理和一系列数据增强技术方面进行了探索，并引入了四种针对历史书写特征设计的新颖的数据增强方法。此外，我们还评估了集成学习策略，以利用经过数据增强训练的模型之间的互补优势。在Gwalther数据集上，我们的最佳单一模型增强（弹性变形）实现了1.86的字符错误率（CER），而前五投票集成则达到了1.60的CER——这一结果相较于此前报告的最佳TrOCR_BASE结果和最先进的方法分别提高了50%和42%。这些结果显示了领域特定的数据增强技术和集成策略在提升历史手稿HTR性能方面的影响。
URL
https://arxiv.org/abs/2508.11499
PDF
-
Improving OCR for Historical Texts of Multiple Languages
2025-08-14 05:52:14Hylke Westerdijk, Ben Blankenborg, Khondoker Ittehadul IslamAbstract
This paper presents our methodology and findings from three tasks across Optical Character Recognition (OCR) and Document Layout Analysis using advanced deep learning techniques. First, for the historical Hebrew fragments of the Dead Sea Scrolls, we enhanced our dataset through extensive data augmentation and employed the Kraken and TrOCR models to improve character recognition. In our analysis of 16th to 18th-century meeting resolutions task, we utilized a Convolutional Recurrent Neural Network (CRNN) that integrated DeepLabV3+ for semantic segmentation with a Bidirectional LSTM, incorporating confidence-based pseudolabeling to refine our model. Finally, for modern English handwriting recognition task, we applied a CRNN with a ResNet34 encoder, trained using the Connectionist Temporal Classification (CTC) loss function to effectively capture sequential dependencies. This report offers valuable insights and suggests potential directions for future research.
Abstract (translated)
本文介绍了我们在光学字符识别（OCR）和文档布局分析三个任务中采用的先进深度学习技术的方法论及发现。首先，对于来自死海古卷的历史希伯来文碎片，我们通过大量数据增强扩展了我们的数据集，并使用Kraken和TrOCR模型提高了字符识别精度。在16至18世纪会议决议文本分析的任务中，我们运用了一种结合了DeepLabV3+语义分割与双向长短期记忆网络（BiLSTM）的卷积递归神经网络（CRNN），并通过基于置信度的伪标签来优化模型。最后，在现代英文手写识别任务中，我们采用了一个带有ResNet34编码器的CRNN，并通过连接主义时间分类（CTC）损失函数进行训练，以有效捕捉序列依赖关系。 本文提供了有价值的见解，并为未来的研究方向提出了建议。
URL
https://arxiv.org/abs/2508.10356
PDF
-
AI-Driven Detection and Analysis of Handwriting on Seized Ivory: A Tool to Uncover Criminal Networks in the Illicit Wildlife Trade
2025-08-13 22:10:42Will Fein, Ryan J. Horwitz, John E. Brown III, Amit Misra, Felipe Oviedo, Kevin White, Juan M. Lavista Ferres, Samuel K. WasserAbstract
The transnational ivory trade continues to drive the decline of elephant populations across Africa, and trafficking networks remain difficult to disrupt. Tusks seized by law enforcement officials carry forensic information on the traffickers responsible for their export, including DNA evidence and handwritten markings made by traffickers. For 20 years, analyses of tusk DNA have identified where elephants were poached and established connections among shipments of ivory. While the links established using genetic evidence are extremely conclusive, genetic data is expensive and sometimes impossible to obtain. But though handwritten markings are easy to photograph, they are rarely documented or analyzed. Here, we present an AI-driven pipeline for extracting and analyzing handwritten markings on seized elephant tusks, offering a novel, scalable, and low-cost source of forensic evidence. Having collected 6,085 photographs from eight large seizures of ivory over a 6-year period (2014-2019), we used an object detection model to extract over 17,000 individual markings, which were then labeled and described using state-of-the-art AI tools. We identified 184 recurring "signature markings" that connect the tusks on which they appear. 20 signature markings were observed in multiple seizures, establishing forensic links between these seizures through traffickers involved in both shipments. This work complements other investigative techniques by filling in gaps where other data sources are unavailable. The study demonstrates the transformative potential of AI in wildlife forensics and highlights practical steps for integrating handwriting analysis into efforts to disrupt organized wildlife crime.
Abstract (translated)
跨国象牙贸易继续导致非洲大象种群的下降，而贩运网络仍然难以破坏。执法官员没收的象牙携带着关于负责其出口的贩运者的法医信息，包括DNA证据和贩运者手工标记的信息。在过去20年里，对象牙DNA的分析已经确定了大象被偷猎的位置，并建立了各批象牙之间的联系。尽管使用遗传证据建立的关联非常有说服力，但遗传数据却昂贵且有时难以获得。然而，虽然手写标记容易拍照，但却很少被记录和分析。在这里，我们提出了一种基于人工智能的手工标记提取和分析被盗大象象牙上手工标记的流程，提供了一个新颖、可扩展且低成本的法医证据来源。在六年期间（2014-2019年）内，从八个大规模象牙没收事件中收集了6,085张照片，我们使用了一种物体检测模型提取出超过17,000个单独的手工标记，并利用最先进的AI工具对其进行标注和描述。我们识别出了184个重复出现的“签名标记”，这些标记将它们出现在其上的象牙连接起来。20个签名标记在多个没收事件中被观察到，通过参与这两个批次运输的相关贩运者建立了各批之间的法医联系。这项研究通过填补其他数据来源不足时出现的信息缺口来补充了其他调查技术。该研究表明人工智能在野生动物法医学中的变革潜力，并强调了将手写分析整合到打击有组织野生动物犯罪努力中的一些实用步骤。
URL
https://arxiv.org/abs/2508.10219
PDF
-
Quo Vadis Handwritten Text Generation for Handwritten Text Recognition?
2025-08-13 16:39:18Vittorio Pippi, Konstantina Nikolaidou, Silvia Cascianelli, George Retsinas, Giorgos Sfikas, Rita Cucchiara, Marcus LiwickiAbstract
The digitization of historical manuscripts presents significant challenges for Handwritten Text Recognition (HTR) systems, particularly when dealing with small, author-specific collections that diverge from the training data distributions. Handwritten Text Generation (HTG) techniques, which generate synthetic data tailored to specific handwriting styles, offer a promising solution to address these challenges. However, the effectiveness of various HTG models in enhancing HTR performance, especially in low-resource transcription settings, has not been thoroughly evaluated. In this work, we systematically compare three state-of-the-art styled HTG models (representing the generative adversarial, diffusion, and autoregressive paradigms for HTG) to assess their impact on HTR fine-tuning. We analyze how visual and linguistic characteristics of synthetic data influence fine-tuning outcomes and provide quantitative guidelines for selecting the most effective HTG model. The results of our analysis provide insights into the current capabilities of HTG methods and highlight key areas for further improvement in their application to low-resource HTR.
Abstract (translated)
历史手稿的数字化对于手写文本识别（HTR）系统带来了显著挑战，特别是在处理与训练数据分布差异较大的小型、特定作者的手稿集合时。生成符合特定书写风格的合成数据的手写文本生成（HTG）技术为解决这些挑战提供了有前景的方法。然而，各种HTG模型在提升资源匮乏环境下的HTR性能方面效果如何尚未得到充分评估。 本文系统地比较了三种最先进的具有风格特性的HTG模型（代表HTG中的生成对抗、扩散和自回归范式），以评估它们对HTR微调的影响。我们分析了合成数据的视觉和语言特征如何影响微调结果，并提供了选择最有效HTG模型的定量指导原则。我们的研究结果揭示了当前HTG方法的能力，强调了在低资源HTR应用中进一步改进的关键领域。
URL
https://arxiv.org/abs/2508.09936
PDF
-
CTC Transcription Alignment of the Bullinger Letters: Automatic Improvement of Annotation Quality
2025-08-11 12:18:41Marco Peer, Anna Scius-Bertrand, Andreas FischerAbstract
Handwritten text recognition for historical documents remains challenging due to handwriting variability, degraded sources, and limited layout-aware annotations. In this work, we address annotation errors - particularly hyphenation issues - in the Bullinger correspondence, a large 16th-century letter collection. We introduce a self-training method based on a CTC alignment algorithm that matches full transcriptions to text line images using dynamic programming and model output probabilities trained with the CTC loss. Our approach improves performance (e.g., by 1.1 percentage points CER with PyLaia) and increases alignment accuracy. Interestingly, we find that weaker models yield more accurate alignments, enabling an iterative training strategy. We release a new manually corrected subset of 100 pages from the Bullinger dataset, along with our code and benchmarks. Our approach can be applied iteratively to further improve the CER as well as the alignment quality for text recognition pipelines. Code and data are available via this https URL.
Abstract (translated)
历史文献的手写文本识别由于书写变化性、退化来源和有限的版面感知标注而仍然具有挑战性。在本研究中，我们解决了布林格通信中的注释错误问题，特别是连字符问题，这是16世纪的一大批信件集合。我们提出了一种基于CTC对齐算法的自训练方法，该方法利用动态规划和使用CTC损失训练得到的概率模型输出，将全文转录与文本行图像进行匹配。我们的方法提高了性能（例如，在PyLaia中字符错误率降低了1.1个百分点），并增加了对齐准确性。有趣的是，我们发现较弱的模型产生了更准确的对齐结果，这使迭代训练策略成为可能。 我们发布了从布林格数据集中手动修正的一个包含100页的新子集，并提供了我们的代码和基准测试结果。我们的方法可以被反复应用于进一步提高字符错误率（CER）以及文本识别管道中的对准质量。代码和数据可通过此链接获取：[请在此插入链接]。 原文献中的网址无法直接显示，您可以在相应的研究发布平台上查找该论文的官方链接以访问相关资源。
URL
https://arxiv.org/abs/2508.07904
PDF
-
When Deep Learning Fails: Limitations of Recurrent Models on Stroke-Based Handwriting for Alzheimer's Disease Detection
2025-08-05 11:10:11Emanuele Nardone, Tiziana D'Alessandro, Francesco Fontanella, Claudio De StefanoAbstract
Alzheimer's disease detection requires expensive neuroimaging or invasive procedures, limiting accessibility. This study explores whether deep learning can enable non-invasive Alzheimer's disease detection through handwriting analysis. Using a dataset of 34 distinct handwriting tasks collected from healthy controls and Alzheimer's disease patients, we evaluate and compare three recurrent neural architectures (LSTM, GRU, RNN) against traditional machine learning models. A crucial distinction of our approach is that the recurrent models process pre-extracted features from discrete strokes, not raw temporal signals. This violates the assumption of a continuous temporal flow that recurrent networks are designed to capture. Results reveal that they exhibit poor specificity and high variance. Traditional ensemble methods significantly outperform all deep architectures, achieving higher accuracy with balanced metrics. This demonstrates that recurrent architectures, designed for continuous temporal sequences, fail when applied to feature vectors extracted from ambiguously segmented strokes. Despite their complexity, deep learning models cannot overcome the fundamental disconnect between their architectural assumptions and the discrete, feature-based nature of stroke-level handwriting data. Although performance is limited, the study highlights several critical issues in data representation and model compatibility, pointing to valuable directions for future research.
Abstract (translated)
阿尔茨海默病的检测通常需要昂贵的神经影像技术或侵入性操作，这限制了其在实际中的应用。本研究探索了一种通过分析手写来实现非侵入式阿尔茨海默病诊断的可能性，并使用深度学习技术进行这项任务。我们采用了一个包含34个不同手写任务的数据集，这些数据来自健康对照组和阿尔茨海默病患者。在这项研究中，评估并比较了三种递归神经网络架构（LSTM、GRU、RNN）与传统机器学习模型的性能。 本研究的一个关键特点是，递归模型处理的是从离散笔划中预先提取出来的特征，而不是原始的时间序列信号。这违背了递归网络设计初衷——用于捕捉连续时间流的特点。实验结果显示，这些模型表现出较差的特异性和较高的方差。 相比之下，传统的集成方法在所有深度架构上都表现出了显著的优势，并且能够实现更高的准确度以及平衡的性能指标。这一结果表明，当应用于从模糊划分笔划中提取出来的特征向量时，设计用于连续时间序列的递归架构无法有效工作。尽管这些深度学习模型复杂度很高，但它们未能克服其结构假设与基于离散、特征化的笔画级手写数据之间本质上的不兼容性。 虽然这项研究显示了性能限制，但它揭示了一些在数据表示和模型兼容性方面的重要问题，并为未来的研究指明了有价值的方向。
URL
https://arxiv.org/abs/2508.03773
PDF
-
Capturing More: Learning Multi-Domain Representations for Robust Online Handwriting Verification
2025-08-02 16:20:35Peirong Zhang, Kai Ding, Lianwen JinAbstract
In this paper, we propose SPECTRUM, a temporal-frequency synergistic model that unlocks the untapped potential of multi-domain representation learning for online handwriting verification (OHV). SPECTRUM comprises three core components: (1) a multi-scale interactor that finely combines temporal and frequency features through dual-modal sequence interaction and multi-scale aggregation, (2) a self-gated fusion module that dynamically integrates global temporal and frequency features via self-driven balancing. These two components work synergistically to achieve micro-to-macro spectral-temporal integration. (3) A multi-domain distance-based verifier then utilizes both temporal and frequency representations to improve discrimination between genuine and forged handwriting, surpassing conventional temporal-only approaches. Extensive experiments demonstrate SPECTRUM's superior performance over existing OHV methods, underscoring the effectiveness of temporal-frequency multi-domain learning. Furthermore, we reveal that incorporating multiple handwritten biometrics fundamentally enhances the discriminative power of handwriting representations and facilitates verification. These findings not only validate the efficacy of multi-domain learning in OHV but also pave the way for future research in multi-domain approaches across both feature and biometric domains. Code is publicly available at this https URL.
Abstract (translated)
在这篇论文中，我们提出了一种称为SPECTRUM的时频协同模型，该模型解锁了在线手写验证（OHV）中多领域表示学习未被充分利用的潜力。SPECTRUM包含三个核心组件： 1. **一个多尺度交互器**：通过双模态序列互动和多层次聚合，精细地结合时间与频率特征。 2. **自门控融合模块**：动态整合全局时间和频率特征，并通过自我驱动平衡实现这一过程。 这两个部分协同工作，实现了从微观到宏观的频谱-时间集成。 3. **一个多领域距离基验证器**：利用时间和频率表示来改进真实手写和伪造手写的区分度，超越了传统的仅基于时间的方法。 广泛的实验表明，SPECTRUM在现有的OHV方法中表现出色，强调了时频多领域学习的有效性。此外，我们揭示了整合多种手写生物特征从根本上增强了手写表示的判别力，并促进了验证过程。这些发现不仅证明了多领域学习在OHV中的有效性，而且为未来研究开辟了跨特征和生物特征领域的多领域方法的道路。 代码可在此 URL 公开获取：[https://this-url.com](https://this-url.com)
URL
https://arxiv.org/abs/2508.01427
PDF
-
A Hybrid Multi-Well Hopfield-CNN with Feature Extraction and K-Means for MNIST Classification
2025-07-11 17:26:06Ahmed FarooqAbstract
This study presents a hybrid model for classifying handwritten digits in the MNIST dataset, combining convolutional neural networks (CNNs) with a multi-well Hopfield network. The approach employs a CNN to extract high-dimensional features from input images, which are then clustered into class-specific prototypes using k-means clustering. These prototypes serve as attractors in a multi-well energy landscape, where a Hopfield network performs classification by minimizing an energy function that balances feature similarity and class this http URL model's design enables robust handling of intraclass variability, such as diverse handwriting styles, while providing an interpretable framework through its energy-based decision process. Through systematic optimization of the CNN architecture and the number of wells, the model achieves a high test accuracy of 99.2% on 10,000 MNIST images, demonstrating its effectiveness for image classification tasks. The findings highlight the critical role of deep feature extraction and sufficient prototype coverage in achieving high performance, with potential for broader applications in pattern recognition.
Abstract (translated)
这项研究提出了一种用于在MNIST数据集上分类手写数字的混合模型，该模型结合了卷积神经网络（CNN）与多阱霍普菲尔德网络。这种方法利用CNN从输入图像中提取高维特征，并使用k均值聚类将这些特征聚类为特定于每个类别的原型。这些原型作为具有多个能量陷阱的能量景观中的吸引子，在其中霍普菲尔德网络通过最小化一个平衡了特征相似性和类别归属的能函数来进行分类。该模型的设计能够稳健地处理同一类别内的变化，例如多样的手写风格，并且由于其基于能量的决策过程提供了可解释性框架。 通过对CNN架构和阱的数量进行系统优化，该模型在10,000张MNIST图像上达到了99.2%的高测试准确率，证明了它对于图像分类任务的有效性。研究结果强调了深度特征提取以及充分原型覆盖对于实现高性能的关键作用，并且其潜在的应用范围可能更广泛，在模式识别领域具有潜力。
URL
https://arxiv.org/abs/2507.08766
PDF
-
SSSUMO: Real-Time Semi-Supervised Submovement Decomposition
2025-07-08 21:26:25Evgenii Rudakov, Jonathan Shock, Otto Lappi, Benjamin Ultan CowleyAbstract
This paper introduces a SSSUMO, semi-supervised deep learning approach for submovement decomposition that achieves state-of-the-art accuracy and speed. While submovement analysis offers valuable insights into motor control, existing methods struggle with reconstruction accuracy, computational cost, and validation, due to the difficulty of obtaining hand-labeled data. We address these challenges using a semi-supervised learning framework. This framework learns from synthetic data, initially generated from minimum-jerk principles and then iteratively refined through adaptation to unlabeled human movement data. Our fully convolutional architecture with differentiable reconstruction significantly surpasses existing methods on both synthetic and diverse human motion datasets, demonstrating robustness even in high-noise conditions. Crucially, the model operates in real-time (less than a millisecond per input second), a substantial improvement over optimization-based techniques. This enhanced performance facilitates new applications in human-computer interaction, rehabilitation medicine, and motor control studies. We demonstrate the model's effectiveness across diverse human-performed tasks such as steering, rotation, pointing, object moving, handwriting, and mouse-controlled gaming, showing notable improvements particularly on challenging datasets where traditional methods largely fail. Training and benchmarking source code, along with pre-trained model weights, are made publicly available at this https URL.
Abstract (translated)
本文介绍了一种名为SSSUMO的半监督深度学习方法，用于次运动分解，该方法实现了最先进的准确性和速度。虽然次运动分析为对运动控制的理解提供了有价值的见解，但现有方法在重建精度、计算成本和验证方面面临着挑战，这主要是由于难以获取手动标注的数据所导致的问题。我们通过使用一种基于合成数据的半监督学习框架来解决这些问题。该框架首先从最小化位移的原则生成初始数据，并且通过不断迭代地适应未标记的人体运动数据来进行优化。我们的全卷积架构和可微重构显著超越了现有的方法，不仅在合成数据集上，在多样化的人类动作数据集上也表现出色，即使在高噪音条件下也能展现出强大的鲁棒性。特别重要的是，该模型可以在实时环境中运行（每秒输入处理时间少于一毫秒），这远远优于基于优化的方法。这种性能的提升为人类与计算机交互、康复医学和运动控制研究等新领域的应用开辟了道路。我们通过驾驶、旋转、指向、物体移动、书写以及鼠标控制游戏等一系列多样化的人类任务，展示了该模型的有效性，并且在传统方法表现不佳的数据集上显示出了显著的进步。训练和基准测试的源代码，以及预训练模型权重已公开提供，在此网址：[URL]（请将[URL]替换为实际提供的链接）。
URL
https://arxiv.org/abs/2507.08028
PDF
-
Advancing Offline Handwritten Text Recognition: A Systematic Review of Data Augmentation and Generation Techniques
2025-07-08 12:03:58Yassin Hussein Rassul, Aram M. Ahmed, Polla Fattah, Bryar A. Hassan, Arwaa W. Abdulkareem, Tarik A. Rashid, Joan LuAbstract
Offline Handwritten Text Recognition (HTR) systems play a crucial role in applications such as historical document digitization, automatic form processing, and biometric authentication. However, their performance is often hindered by the limited availability of annotated training data, particularly for low-resource languages and complex scripts. This paper presents a comprehensive survey of offline handwritten data augmentation and generation techniques designed to improve the accuracy and robustness of HTR systems. We systematically examine traditional augmentation methods alongside recent advances in deep learning, including Generative Adversarial Networks (GANs), diffusion models, and transformer-based approaches. Furthermore, we explore the challenges associated with generating diverse and realistic handwriting samples, particularly in preserving script authenticity and addressing data scarcity. This survey follows the PRISMA methodology, ensuring a structured and rigorous selection process. Our analysis began with 1,302 primary studies, which were filtered down to 848 after removing duplicates, drawing from key academic sources such as IEEE Digital Library, Springer Link, Science Direct, and ACM Digital Library. By evaluating existing datasets, assessment metrics, and state-of-the-art methodologies, this survey identifies key research gaps and proposes future directions to advance the field of handwritten text generation across diverse linguistic and stylistic landscapes.
Abstract (translated)
离线手写文本识别（HTR）系统在历史文档数字化、自动表单处理和生物特征认证等应用中扮演着重要角色。然而，其性能往往受到注释训练数据可用性有限的限制，尤其是对于资源匮乏的语言和复杂的书写系统。本文综述了用于提高HTR系统准确性和鲁棒性的离线手写数据增强和生成技术。我们系统地考察了传统增广方法以及深度学习领域的最新进展，包括生成对抗网络（GANs）、扩散模型和基于变压器的方法。此外，还探讨了生成多样且现实的手写样本的挑战，特别是保持书写真实性及应对数据稀缺问题。本次综述遵循PRISMA方法论，确保了一个结构化和严谨的选择过程。我们的分析始于1,302项初步研究，并在去除重复后筛选至848项，这些研究主要来源于IEEE数字图书馆、Springer Link、Science Direct和ACM数字图书馆等关键学术来源。通过评估现有的数据集、评价指标及前沿方法论，本综述指出了关键的研究缺口，并提出了未来发展方向，以推进跨越多样化语言和书写风格的手写文本生成领域的进步。
URL
https://arxiv.org/abs/2507.06275
PDF
-
RefTok: Reference-Based Tokenization for Video Generation
2025-07-03 17:59:55Xiang Fan, Xiaohang Sun, Kushan Thakkar, Zhu Liu, Vimal Bhat, Ranjay Krishna, Xiang HaoAbstract
Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies inherent in videos. To address this limitation, we introduce RefTok, a novel reference-based tokenization method capable of capturing complex temporal dynamics and contextual information. Our method encodes and decodes sets of frames conditioned on an unquantized reference frame. When decoded, RefTok preserves the continuity of motion and the appearance of objects across frames. For example, RefTok retains facial details despite head motion, reconstructs text correctly, preserves small patterns, and maintains the legibility of handwriting from the context. Across 4 video datasets (K600, UCF-101, BAIR Robot Pushing, and DAVIS), RefTok significantly outperforms current state-of-the-art tokenizers (Cosmos and MAGVIT) and improves all evaluated metrics (PSNR, SSIM, LPIPS) by an average of 36.7% at the same or higher compression ratios. When a video generation model is trained using RefTok's latents on the BAIR Robot Pushing task, the generations not only outperform MAGVIT-B but the larger MAGVIT-L, which has 4x more parameters, across all generation metrics by an average of 27.9%.
Abstract (translated)
有效地处理时间冗余仍然是学习视频模型的关键挑战。当前的主流方法通常将每一组帧独立看待，未能有效捕捉视频中固有的时间和冗余关系。为了解决这一局限性，我们引入了RefTok，这是一种新型基于参考的标记化方法，能够捕获复杂的时态动态和上下文信息。我们的方法在未量化的参考帧条件下编码和解码一组帧。当进行解码时，RefTok保持了跨帧之间的运动连续性和对象外观的一致性。例如，即使头部有动作，RefTok也能保留面部细节；正确重构文本内容；保持小图案的完整性，并从上下文中维持手写的可读性。 在四个视频数据集（K600、UCF-101、BAIR机器人推拉任务和DAVIS）上，RefTok显著优于目前最先进的标记化方法（Cosmos 和 MAGVIT），并且在同一或更高的压缩比下，改进了所有评估指标（PSNR、SSIM、LPIPS），平均提高了36.7%。 当使用RefTok的潜在表示在BAIR机器人推拉任务上训练视频生成模型时，所产生的结果不仅超过了MAGVIT-B，在所有生成指标中平均高出27.9%，还超越了参数量是其4倍的更大规模模型MAGVIT-L。
URL
https://arxiv.org/abs/2507.02862
PDF
