Historical documents from Late Antiquity to the early Middle Ages often sufer from degraded image quality due to aging, inadequate preservation, and environmental factors, presenting significant challenges for paleographical analysis. These documents contain crucial graphical symbols representing administrative, economic, and cultural information, which are time-consuming and error-prone to interpret manually. This research investigates image processing algorithms and deep learning models for enhancing these historical documents. Using image processing techniques, we improve symbol readability and visibility, while our deep learning approach aids in reconstructing degraded content and identifying patterns. This work contributes to improving the quality of historical document analysis, particularly for graphical symbol interpretation in paleographical studies.
The field of paleography has experienced significant advancement through digital technologies,
particularly in the analysis and preservation of historical documents [
Several datasets are available for evaluating enhancement and analysis techniques applied to historical
documents. These include graphic symbols from documentary records dating from Late Antiquity to
the early medieval period [
In this research, we utilize the dataset of the project (NOTAE): NOT A writtEn word but graphic
symbols [
In historical document processing, significant advancements have been made in enhancing and analyzing
ancient manuscripts through image-processing techniques and deep learning approaches. This section
reviews key studies relevant to document image enhancement, highlighting their strengths, limitations,
and how our approach builds upon these methods. Traditional image-processing techniques have
played a crucial role in document enhancement, particularly for restoring degraded historical texts.
Atanasiu and Marthot-Santaniello [
This section explores two distinct image processing approaches alongside a deep learning method to enhance the quality of graphical symbols. These techniques aim to improve readability, enhance contrast, mitigate illumination variations, and uncover hidden details. By comparing the efectiveness of diferent methods, we identify the most suitable approaches for the specific goal of graphical symbol enhancement, enabling the extraction of valuable insights and fostering a deeper understanding of these ancient symbols.
Image processing techniques play a crucial role in enhancing image quality and addressing various challenges across diferent datasets. For ancient graphical symbols from the medieval period, edge detection and superpixel segmentation are employed to reveal hidden details and preserve intricate patterns. Histogram equalization and adaptive histogram equalization enhance contrast and address illumination variations, resulting in more visible and interpretable symbols. Model A and B, described in the following, implement these ideas.
This model implements a comprehensive enhancement pipeline combining edge detection with advanced
segmentation techniques. The enhancement process consists of three main stages: edge detection,
superpixel segmentation, and histogram optimization. In the initial stage, we employ the Sobel operator
for edge detection [
(, ) = ≈ ( + 1, ) − ( − 1, )
(, ) = ≈ (, + 1) − (, − 1)
√︁ (, ) =
(, )2 + (, )2 where and denote the approximated gradients in the horizontal and vertical directions, respectively. The gradient magnitude (, ) is then computed as:
Following edge detection, we implement the Simple Linear Iterative Clustering (SLIC) algorithm [
√︃ (, ) = 2 + ︂( )︂ 2 2 where: • = √︀( − )2 + ( − )2 + ( − )2 is the color distance • = √︀( − )2 + ( − )2 is the spatial distance • represents the sampling interval in the pixel grid • is a compactness parameter controlling the relative importance of spatial proximity The final enhancement stage employs adaptive histogram equalization. For each intensity level , we compute the cumulative distribution function ():
() = ∑︁ (), ∈ [0, − 1] =0 (1) (2) (3) (4) (5) where () represents the probability of occurrence of intensity level , and is the total number of possible intensity levels. The new intensity value is then calculated as:
(, ) = ( − 1) · ((, ))
This transformation is applied locally within adaptive windows to account for spatial variations in contrast and illumination. The efectiveness of this approach is demonstrated in Figure 1, where significant improvements in both local contrast and edge definition are achieved while preserving the structural integrity of the historical symbols.
The enhancement process is applied iteratively until a convergence criterion is met: |+1 − |2 < where represents the enhanced image at iteration , and | · | 2 denotes the L2-norm. In our experiments, we use a normalized convergence threshold = 10− 4 · | 0|2, where 0 is the initial image. This relative threshold ensures the stopping criterion scales appropriately with image size and intensity range, providing consistent convergence behavior across diferent input images. (6) (7)
The second model focuses on noise reduction while preserving symbol structures through a two-phase process. The first phase, apply_filter , combines edge detection and watershed segmentation with SLIC superpixels to create an initial enhanced representation. The second phase, remove_noise, implements morphological operations for noise reduction.
The process begins with binary thresholding to separate foreground and background elements. This is followed by morphological opening operations that efectively remove small artifacts while maintaining the integrity of larger structures. The final step combines the cleaned binary image with the enhanced version to produce the result shown in Figure 2.
Our deep learning approach incorporates synthetic data generation and transformer-based feature extraction to enhance historical document images [22]. The system utilizes a Faster R-CNN model [23] trained on both original and synthetically generated data, enabling the preservation of unique document characteristics. The OPTICS algorithm [24] is employed for stroke segmentation, with adaptive circle construction handling variable stroke thickness. Figure 3 demonstrates the efectiveness of this approach. Following the ideas used by Cai et al. [25], our study explores how GAN-based synthetic data generation can improve symbol recognition in ancient documents. By creating enriched training datasets that reflect the diverse and complex nature of historical symbols, we aim to achieve higher accuracy and reliability in symbol detection for document analysis. The enriched datasets generated facilitate a more comprehensive training environment, significantly enhancing the models’ ability to generalize across new and unseen data. This capability is vital for practical applications where models are expected to perform accurately outside their training set. Moreover, integrating synthetic data that accurately reflects the complexity of real-world scenarios reduces the models’ tendencies to overfit the limited nuances of smaller datasets. Instead, they learn more robust features that represent the true underlying patterns in the data, substantially boosting performance and generalizability.
This section presents a detailed evaluation and comparative analysis of our three proposed approaches: Model A (edge detection and segmentation), Model B (noise reduction and enhancement), and the deep learning-based method. Through quantitative metrics and visual examples, we assess each method’s efectiveness in enhancing historical documents and preserving graphical symbols. The comparison examines multiple performance aspects including edge preservation, contrast enhancement, noise reduction, and symbol reconstruction capabilities. Special attention is given to challenging cases, such as severely degraded documents and partially missing symbols, to thoroughly understand each method’s strengths and limitations. The analysis includes comparisons with existing solutions, particularly the Hierax method, to demonstrate the advancements achieved by our approaches.
To evaluate the efectiveness of our approaches, we conducted the comparative analysis using challenging low-quality images (one example is shown in Figure 4). As discussed in the following, Model A demonstrated superior edge preservation and contrast enhancement, while Model B excelled in noise reduction and structure preservation. The deep learning approach showed particular strength in reconstructing degraded regions and pattern recognition.
When compared to existing approaches in historical document enhancement, such as Hierax [26]1, our method represents a better advancement in revealing details that were previously obscured, as illustrated in Figure 5.
To quantitatively evaluate and compare our approaches, we employed several standard image quality metrics and developed specific measurements for historical document enhancement. The evaluation was conducted on a test set of 100 historical document images containing various types of degradation and symbols. The metrics taken into account are summarized below.
PSNR = 10 · log10 ︂( 2 )︂
MSE where is the maximum possible pixel value, and MSE is the Mean Square Error between the enhanced and reference images.
SSIM(, ) =
(2 + 1)(2 + 2) ( 2 + 2 + 1)( 2 + 2 + 2) where , are local means, 2, 2 are variances, and is the covariance.
SPR = preserved total where preserved is the number of correctly preserved symbols and total is the total number of symbols in the original image.
Edge Preservation Assessment For edge preservation evaluation, we computed the Edge Preservation Index (EPI):
EPI = ∑︀, ||∇(, )| − |∇
(, )||2 ∑︀, |∇(, )|2 where ∇ and ∇ are the gradients of enhanced and original images, respectively.
Our experimental results demonstrate the relative strengths of each approach in Table 1. Model A achieved significant improvements in edge preservation and contrast enhancement, with quantitative measurements showing an average improvement of 45% in contrast ratio and 38% in edge preservation compared to baseline measurements. Model B demonstrated exceptional capability in noise reduction, achieving a 52% reduction in background noise while maintaining 94% of essential edge information. The deep learning approach showed a 73% accuracy in reconstructing damaged symbols, particularly excelling in areas where traditional methods struggled. Model A achieved superior performance in edge preservation and contrast enhancement achieving a PSNR of 32.4 dB and an SSIM of 0.89, indicating better preservation of structural information and overall image quality. The high SPR of 94.2% confirms its efectiveness in maintaining symbol integrity during the enhancement process.
Model B excelled in noise reduction while maintaining edge preservation (EPI: 0.85), making it particularly efective for badly degraded documents. The deep learning approach, despite lower traditional metric scores (PSNR: 29.5 dB, SSIM: 0.84), demonstrated superior symbol reconstruction and pattern recognition, especially in cases of severely degraded or missing symbols, as illustrated in Figure 3.
This study investigates image enhancement techniques for historical documents by integrating traditional image processing with deep learning. Our proposed methods consistently outperform the Hierax approach across various metrics. Model A excels in edge preservation and contrast enhancement, while Model B is more efective for noise reduction and structural preservation. The deep learning model, though slightly lower in traditional metrics, proves superior in reconstructing damaged symbols and handling severely degraded cases. Each method has distinct strengths suited to diferent document conditions. While tested on the NOTAE dataset, our framework’s adaptability suggests broader applicability to collections like DIVA-HisDB and IAM-HistDB. Future work will focus on a hybrid system with an adaptive selection mechanism and human-in-the-loop validation to optimize enhancement based on document conditions. (2012) 2274–2282. [22] Z. Ziran, F. Leotta, M. Mecella, Enhancing object detection in ancient documents with synthetic data generation and transformer-based models, 2023. URL: https://arxiv.org/abs/2307.16005. arXiv:2307.16005. [23] S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE transactions on pattern analysis and machine intelligence 39 (2016) 1137–1149. [24] M. Ankerst, M. M. Breunig, H.-P. Kriegel, J. Sander, Optics: Ordering points to identify the clustering structure, ACM Sigmod record 28 (1999) 49–60. [25] J. Cai, L. Peng, Y. Tang, C. Liu, P. Li, Th-gan: generative adversarial network based transfer learning for historical chinese character recognition, in: 2019 International Conference on Document Analysis and Recognition (ICDAR), IEEE, 2019, pp. 178–183. [26] V. Atanasiu, I. Marthot-Santaniello, Hierax legibility enhancement software, 2020.