Search Results (53)

Irregular Hangeul typefaces present a challenging computer vision problem because complete font generation must generalize from a small number of reference glyphs while preserving both structural consistency and stylistic fidelity. This study investigates few-shot learning for the restoration and expansion of irregular and historical Hangeul typefaces through three experiments spanning relatively regular woodblock print, irregular contemporary type, and highly irregular royal calligraphy. We benchmark a GAN-based model (DM-Font), a VQGAN-based model (VQ-Font), and a diffusion-based model (Diff-Font) under limited supervision and evaluate them using pixel-level similarity, structural indicator, OCR usability, and expert assessment. DM-Font established a feasible baseline for historical restoration (mean SSIM 0.77), whereas VQ-Font obtained the highest structural similarity for irregular contemporary typeface when paired with a structurally designed 10-character pangram reference set (SSIM 0.97; OCR accuracy 99.5% on the evaluated glyph set). For highly irregular royal calligraphy, the two models performed comparably on global similarity (SSIM 0.78 vs. 0.80) and on expert ratings (4.2 vs. 4.3); VQ-Font showed more stable structure-sensitive indicators, whereas Diff-Font better preserved stylistic nuance. The findings suggest that reference-set composition substantially affects generation quality under fixed-budget few-shot conditions, and that model choice should be matched to source regularity and restoration objectives. Full article

To address prevalent challenges in stone inscription character detection—including glyph blurring, incompleteness, densely arranged characters, and substantial inter-object scale variation—this paper proposes PMN-YOLO, a lightweight, enhanced detection model built upon YOLOv11n. To enhance the detection performance of stele characters in complex scenarios, PP-LCNet is introduced to replace the original feature extraction structure. This not only reduces the model complexity but also enhances the feature expression ability for complex textures and blurred characters, providing effective support for subsequent recognition tasks. Consequently, the proposed model achieves a better balance between detection precision and computational efficiency. Second, we designed the MSAM-smallTarget module specifically for detecting small targets. By integrating multi-scale convolutional operations with spatial attention mechanisms, this module significantly enhances the model’s ability to perceive fine-grained features as well as blurred or fragmented characters commonly found in inscriptions. Furthermore, leveraging small convolutional kernels, dilated convolutions, and lightweight convolutional designs enables adaptive expansion of the receptive field while effectively constraining parameter count. Third, the NWD loss function based on the Wasserstein distance is introduced to replace the traditional IoU metric with a distribution-based similarity measure, thereby significantly improving the model’s localization robustness in scenarios involving densely distributed targets and ambiguous boundaries. The experimental results show that on the self-built stone inscription dataset, the precision of PMN-YOLO reaches 98.3%, the recall rate is 75.5%, and the mAP@50 and mAP@50-95 are 82.7% and 65.0% respectively. The model has 8.7% fewer parameters than the baseline. This method achieves lightweight performance and high detection accuracy, delivering a practical approach to automatically detect and digitally safeguard stone inscriptions. Full article

Scene text–image generation aims to synthesize natural images containing readable and visually coherent text. Although recent diffusion-based methods have shown promising results, they often struggle with low-resource Southeast Asian languages because of complex glyph structures, limited language resources, and weak alignment between generated text and background carriers. To address this issue, we propose FG-Text-SD, a training-free controllable scene text–image generation framework built on Stable Diffusion. The proposed framework organizes multiple text instances in an instance-level manner, injects rendered glyph structure priors into the denoising process to stabilize complex character shapes, modulates cross-attention with carrier-aware masks to improve text-to-surface alignment, and employs OCR-guided local repainting to correct residual local errors. Experiments are conducted on AnyText-benchmark, CVTG-2K, and a newly constructed evaluation set covering Thai, Lao, Khmer, and Burmese. The proposed method achieves strong performance on both public benchmarks and low-resource language subsets, improving text accuracy, readability, and spatial consistency without additional model retraining. These results demonstrate that FG-Text-SD provides an effective solution for controllable scene text–image generation in low-resource multilingual settings. Full article

Historical rubbing images often suffer from stroke breakage, material loss, uneven background interference, and age-related degradation, which make broken-stroke restoration in masked regions difficult. This challenge is particularly severe for oracle bone rubbings, where sparse strokes and damaged radicals require both structural continuity and local texture realism. To address this problem, we propose a three-stage generative adversarial image inpainting framework and evaluate it on oracle bone rubbing images as a focused case study. Stage I employs an LBP-guided coarse completion network to recover local binary texture priors in missing regions. Stage II introduces spatial-attention refinement and a dual-discriminator strategy to improve stroke continuity and local realism. Stage III uses a Swin-based refinement network to model long-range dependencies and enhance global consistency. A composite optimization objective combining reconstruction, weighted hole, perceptual, style, total-variation, and adversarial terms is used to coordinate the three stages. Experiments on oracle bone rubbing images with masking ratios from 10% to 40% show that the proposed framework produces visually coherent restorations and competitive quantitative results, reaching up to 35.18 dB PSNR and 0.9906 SSIM under the 10–20% masking setting. Because oracle bone glyph morphology is highly specialized, the current validation is intentionally restricted to this domain rather than overstating cross-domain generalization. The results show that the proposed framework can support digital conservation and recognition-oriented analysis of damaged oracle bone rubbing images. Full article

Printed Arabic Optical Character Recognition (OCR) remains challenging due to complex glyph morphology, typographic variability, and sensitivity to Unicode-preserved evaluation protocols. This work introduces a methodology that explicitly treats decoding strategy and orthographic normalization as primary experimental variables in multi-font Arabic OCR evaluation. A CNN–Transformer encoder trained with Connectionist Temporal Classification (CTC) is employed as a controlled backbone to isolate the effects of inference configuration and text normalization. Through systematic analysis on the APTI benchmark, we demonstrate that decoding policy and diacritic handling significantly influence reported recognition performance. In particular, language-model-guided decoding yields substantial improvements over greedy decoding, while Unicode-preserved evaluation introduces systematic orthographic inflation driven by deterministic diacritic mismatch. These effects are further amplified by strong cross-font variability. The proposed normalization-aware evaluation framework disentangles structural recognition errors from protocol-induced artifacts, providing a more controlled and reproducible basis for Arabic OCR benchmarking. Full article

The Babylonian numeral system, developed more than four thousand years ago, is one of the earliest known positional number systems, employing a sexagesimal (base-60) structure and a limited set of wedge-shaped symbols. Despite their visual simplicity, Babylonian numerals exhibit substantial structural and positional complexity, particularly when multiple symbols are combined to represent larger numerical values. This complexity presents significant challenges for modern computational recognition, especially in handwritten and degraded archaeological contexts. Most existing research has focused on the recognition of isolated Babylonian numeral symbols, which does not adequately reflect real inscriptions where numerals typically appear as composite sequences. To address this limitation, this paper proposes a hybrid deep learning framework capable of identifying, interpreting, and computing the decimal values of multi-symbol handwritten Babylonian numerals. Building on prior work in single-symbol recognition, we construct a synthetic yet realistic dataset of composite numeral images by combining handwritten glyphs into sequences of two to four symbols while incorporating natural variations in spacing, alignment, and handwriting style. The proposed framework integrates a Convolutional Neural Network (CNN) for visual feature extraction with optional structural feature fusion, followed by a Support Vector Machine (SVM) classifier for reliable multi-class discrimination. A rule-based positional decoder is then applied to convert recognized symbol sequences into their corresponding decimal values using Babylonian base-60 logic. By combining visual recognition with positional numerical reasoning, the proposed system enables end-to-end interpretation of handwritten Babylonian numeral sequences. To the best of our knowledge, this work represents one of the first approaches to jointly classify, decode, and compute numerical values from multi-symbol handwritten Babylonian numerals, contributing to digital epigraphy, archaeological text analysis, and cultural heritage preservation. Full article

Low-flow liquid chromatography has become the primary tool for advanced chromatographic analysis and is an indispensable technique for the sensitive detection of biomolecules. In this study, we developed a new 4-tritylphenyl methacrylate-based monolithic nano-column with an internal diameter of 20 µm for bioanalytical separations in nano-liquid chromatography (nano-LC). The composition of the monolith was optimized with regard to the monomer and porogenic solvent. The column was characterized using Fourier Transformed Infrared Spectroscopy (FT-IR) spectroscopy, scanning electron microscopy (SEM) and chromatographic analyses. Chromatographic characterization was performed using homologous alkylbenzenes (ABs) and polyaromatic hydrocarbons (PAHs), which facilitate hydrophobic and π–π interactions. Run-to-run and column-to-column reproducibility values were found to be <2.51% and 2.4–3.2%, respectively. The final monolith was then used to separate six standard proteins, including β-lactoglobulin A, carbonic anhydrase, ribonuclease A (RNase A), α-chymotrypsinogen (α-chym), lysozyme (Lys), cytochrome C (Cyt C) and myoglobin (Myo), as well as three dipeptides: Alanine-tyrosine (Ala-Tyr), Glycine-phenylalanine (Gly-Phe) and L-carnosine. The nano-column was then applied to profiling peptides and proteins in the MCF-7 cell line, enabling high-resolution peptide analysis. Full article

Generating non-standard fonts, such as running script (e.g., XingShu), poses significant challenges due to their high stroke continuity, structural flexibility, and stylistic diversity, which traditional component-based prior knowledge methods struggle to model effectively. While diffusion models excel at capturing continuous feature spaces and stroke variations through iterative denoising, they face critical limitations: (1) style leakage, where large stylistic differences lead to inconsistent outputs due to noise interference; (2) structural distortion, caused by the absence of explicit structural guidance, resulting in broken strokes or deformed glyphs; and (3) style confusion, where similar font styles are inadequately distinguished, producing ambiguous results. To address these issues, we propose a novel skeleton-guided diffusion model with three key innovations: (1) a skeleton-constrained style rendering module that enforces semantic alignment and balanced energy constraints to amplify critical skeletal features, mitigating style leakage and ensuring stylistic consistency; (2) a cross-scale skeleton preservation module that integrates multi-scale glyph skeleton information through cross-dimensional interactions, effectively modeling macro-level layouts and micro-level stroke details to prevent structural distortions; (3) a contrastive style refinement module that leverages skeleton decomposition and recombination strategies, coupled with contrastive learning on positive and negative samples, to establish robust style representations and disambiguate similar styles. Extensive experiments on diverse font datasets demonstrate that our approach significantly improves the generation quality, achieving superior style fidelity, structural integrity, and style differentiation compared to state-of-the-art diffusion-based font generation methods. Full article

Ancient Chinese scripts—including oracle bone carvings, bronze inscriptions, stone steles, Dunhuang scrolls, and bamboo slips—are rich in historical value but often degraded due to centuries of erosion, damage, and stylistic variability. These issues severely hinder manual transcription and render conventional OCR techniques inadequate, as they are typically trained on modern printed or handwritten text and lack interpretability. To tackle these challenges, we propose FAIR-Net, a hybrid architecture that combines the unsupervised feature learning capacity of a deep autoencoder with the semantic transparency of a fuzzy rule-based classifier. In FAIR-Net, the deep autoencoder first compresses high-resolution character images into low-dimensional, noise-robust embeddings. These embeddings are then passed into a Fuzzy Neural Network (FNN), whose hidden layer leverages Fuzzy C-Means (FCM) clustering to model soft membership degrees and generate human-readable fuzzy rules. The output layer uses Iteratively Reweighted Least Squares Estimation (IRLSE) combined with a Softmax function to produce probabilistic predictions, with all weights constrained as linear mappings to maintain model transparency. We evaluate FAIR-Net on CASIA-HWDB1.0, HWDB1.1, and ICDAR 2013 CompetitionDB, where it achieves a recognition accuracy of 97.91%, significantly outperforming baseline CNNs (p < 0.01, Cohen’s d > 0.8) while maintaining the tightest confidence interval (96.88–98.94%) and lowest standard deviation (±1.03%). Additionally, FAIR-Net reduces inference time to 25 s, improving processing efficiency by 41.9% over AlexNet and up to 98.9% over CNN-Fujitsu, while preserving >97.5% accuracy across evaluations. To further assess generalization to historical scripts, FAIR-Net was tested on the Ancient Chinese Character Dataset (9233 classes; 979,907 images), achieving 83.25% accuracy—slightly higher than ResNet101 but 2.49% lower than SwinT-v2-small—while reducing training time by over 5.5× compared to transformer-based baselines. Fuzzy rule visualization confirms enhanced robustness to glyph ambiguities and erosion. Overall, FAIR-Net provides a practical, interpretable, and highly efficient solution for the digitization and preservation of ancient Chinese character corpora. Full article

Processing ancient text images presents significant challenges due to severe visual degradation, missing glyph structures, and various types of noise caused by aging. These issues are particularly prominent in Chinese historical documents and stone inscriptions, where diverse writing styles, multi-angle capturing, uneven lighting, and low contrast further hinder the performance of traditional OCR techniques. In this paper, we propose a unified neural framework, UniText, for the detection, recognition, and glyph restoration of Chinese characters in images of historical documents and inscriptions. UniText operates at the character level and processes full-page inputs, making it robust to multi-scale, multi-oriented, and noise-corrupted text. The model adopts a multi-task architecture that integrates spatial localization, semantic recognition, and visual restoration through stroke-aware supervision and multi-scale feature aggregation. Experimental results on our curated dataset of ancient Chinese texts demonstrate that UniText achieves a competitive performance in detection and recognition while producing visually faithful restorations under challenging conditions. This work provides a technically scalable and generalizable framework for image-based document analysis, with potential applications in historical document processing, digital archiving, and broader tasks in text image understanding. Full article

Automated font generation for complex, compositional scripts like Korean Hangul presents a significant challenge due to the 11,172 characters and their complicated component-based structure. While existing component-based methods for font image generation acknowledge the compositional nature of Hangul, they often fail to explicitly leverage the crucial positional semantics of its basic elements as initial, middle, and final components, known as Jamo. This oversight can lead to structural inconsistencies and artifacts in the generated glyphs. This paper introduces a novel two-stage framework that directly addresses this gap by imposing a strong, linguistically informed structural principle on the font image generation process. In the first stage, we employ a You Only Look Once version 8 for Segmentation (YOLOv8-Seg) model, a state-of-the-art instance segmentation network, to decompose Hangul characters into their basic components. Notably, this process generates a dataset of position-aware semantic components, categorizing each jamo according to its structural role within the syllabic block. In the second stage, a conditional Generative Adversarial Network (cGAN) is explicitly conditioned on these extracted positional components to perform style transfer with high structural information. The generator learns to synthesize a character’s appearance by referencing the style of the target components while preserving the content structure of a source character. Our model achieves state-of-the-art performance, reducing L1 loss to 0.2991 and improving the Structural Similarity Index (SSIM) to 0.9798, quantitatively outperforming existing methods like MX-Font and CKFont. This position-guided approach demonstrates significant quantitative and qualitative improvements over existing methods in structured script generation, offering enhanced control over glyph structure and a promising approach for generating font images for other complex, structured scripts. Full article

This paper proposes an innovative technique for representing multidimensional datasets using icons inspired by Chernoff faces. Our approach combines classical projection techniques with the explicit assignment of selected data dimensions to avatar (facial) features, leveraging the innate human ability to interpret facial traits. We introduce a semantic division of data dimensions into intuitive and technical categories, assigning the former to avatar features and projecting the latter into a four-dimensional (or higher) spatial embedding. The technique is implemented as a plugin for the open-source dpVision visualization platform, enabling users to interactively explore data in the form of a swarm of avatars whose spatial positions and visual features jointly encode various aspects of the dataset. Experimental results with synthetic test data and a 12-dimensional dataset of Portuguese Vinho Verde wines demonstrate that the proposed method enhances interpretability and facilitates the analysis of complex data structures. Full article

Named entity recognition (NER) is the basic task of constructing a high-quality knowledge graph, which can provide reliable knowledge in the auxiliary diagnosis of dairy cow disease, thus alleviating problems of missed diagnosis and misdiagnosis due to the lack of professional veterinarians in China. Targeting the characteristics of the Chinese dairy cow diseases corpus, we propose an ensemble Chinese NER model incorporating character-level, pinyin-level, glyph-level, and lexical-level features of Chinese characters. These multi-level features were concatenated and fed into the bidirectional long short-term memory (Bi-LSTM) network based on the multi-head self-attention mechanism to learn long-distance dependencies while focusing on important features. Finally, the globally optimal label sequence was obtained by the conditional random field (CRF) model. Experimental results showed that our proposed model outperformed baselines and related works with an F1 score of 92.18%, which is suitable and effective for named entity recognition for the dairy cow disease corpus. Full article

The total-ion-yield (TIY) near-edge X-ray absorption fine-structure (NEXAFS) spectra of two dipeptides were measured and analyzed to identify the excitation sites of core electrons and the corresponding destination molecular orbitals. Peptide molecules were transferred to the gaseous phase using traditional heating and MALDI methods, ensuring that the resulting NEXAFS spectra and fragmentation products were consistent across both approaches. Mass spectra obtained at various excitation energies revealed the branching ratios of products at each energy level, offering insights into specific dissociation phenomena. Notably, variations in excitation energy demonstrated a selective dissociation process, with certain products forming more efficiently. This specificity appears closely linked to dissociations near the peptide bond, where the nodal planes of destination molecular orbitals are located. These findings were validated using both small peptide models and peptoid molecules, highlighting consistent patterns in the dissociation behavior. Full article

The route of the South-to-North Water Diversion channel strides across part of the coal mine goaf in Yuzhou County, Henan Province, China, and long-term deformation due to coal seam recovery poses a threat to the safe operation of the main canal. Therefore, the study of the deformation mechanisms induced by coal seam recovery is of great significance to the canal’s safe operation, as well as to deformation monitoring and to the development of early warnings. The geologic model was established based on the geological engineering conditions of the Yuzhou Gongmao mining area, spanning the main canal of the South-to-North Water Diversion Project; then, the physical model test was carried out according to similar theories. The deformation characteristics of the rock overlay and the channel above the goaf were analyzed, and failure criteria for overburdened rock and the channel were proposed. The results showed that horizontal fissures were gradually observed in the overlying rock as the coal mining progressed, extending and widening. When the goaf was excavated to 76 cm, the overlying rock body suddenly collapsed as a whole, and the channel collapsed and was destroyed. During the formation of the goaf, there was a critical span ratio (R): When the height-to-span ratio was greater than 0.039, the collapse of overlying rock occurred only within a certain range above the goaf. When the height-to-span ratio was less than 0.039, the overlying rock body collapsed in a wide area, and the soil on both sides of the channel collapsed to the center of the channel, presenting a “V” glyph collapse. The sediment in the center of the channel measured 22 mm, and there were multiple tensile cracks on both sides of the embankment, with a width of 5–10 mm. The vertical deformation of the channel went through three stages, namely, the initial deformation stage, the deceleration deformation stage, and the stability stage. This study can provide scientific guidance for early warnings of channel deformation and safe operation across the goaf. Full article