Effective and fast binarization method for combined degradation on ancient documents

Saddami, Khairun; Munadi, Khairul; Away, Yuwaldi; Arnia, Fitri

doi:10.1016/j.heliyon.2019.e02613

Cited by 19 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preprocessing techniques for image enhancement in OCR for image-to-LaTeX conversion are crucial for improving the accuracy of the recognition process [22,23]. These techniques address challenges related to image quality, noise, contrast, skew, and multimodal features.…”

Section: Preprocessing Techniques For Image Enhancementmentioning

confidence: 99%

“…Various error detection methodologies include statistical analysis, linguistic analysis, and pattern matching. A study compared the OCR output with statistical models to identify discrepancies [22]. Statistical techniques can identify potential errors based on their deviation from the expected patterns by analyzing the frequency and distribution of symbols.…”

Section: Post-processing Techniques For Error Correction In Ocr For I...mentioning

confidence: 99%

“…The correction process becomes more challenging if the OCR system has many errors. Therefore, it is vital to continuously enhance and correct the underlying OCR algorithms to mitigate recognition errors [22]. Improvements in preprocessing techniques like noise reduction, image enhancement, and segmentation lead to better OCR results and consequently enhance the effectiveness of error correction in image-to-LaTeX conversion.…”

Section: Post-processing Strategies Leverage the Redundancy Inherent ...mentioning

confidence: 99%

See 2 more Smart Citations

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Orji,

Haydar,

Erşan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

This paper comprehensively assesses the application of active learning strategies to enhance natural language processing-based optical character recognition (OCR) models for image-to-LaTeX conversion. It addresses the existing limitations of OCR models and proposes innovative practices to strengthen their accuracy. Key components of this study include the augmentation of training data with LaTeX syntax constraints, the integration of active learning strategies, and the employment of active learning feedback loops. This paper first examines the current weaknesses of OCR models with a particular focus on symbol recognition, complex equation handling, and noise moderation. These limitations serve as a framework against which the subsequent research methodologies are assessed. Augmenting the training data with LaTeX syntax constraints is a crucial strategy for improving model precision. Incorporating symbol relationships, wherein contextual information is considered during recognition, further enriches the error correction. This paper critically examines the application of active learning strategies. The active learning feedback loop leads to progressive improvements in accuracy. This article underlines the importance of uncertainty and diversity sampling in sample selection, ensuring that the dynamic learning process remains efficient and effective. Appropriate evaluation metrics and ensemble techniques are used to improve the operational learning effectiveness of the OCR model. These techniques allow the model to adapt and perform more effectively in diverse application domains, further extending its utility.

show abstract

Section: Preprocessing Techniques For Image Enhancementmentioning

confidence: 99%

Section: Post-processing Techniques For Error Correction In Ocr For I...mentioning

confidence: 99%

Section: Post-processing Strategies Leverage the Redundancy Inherent ...mentioning

confidence: 99%

See 1 more Smart Citation

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Orji,

Haydar,

Erşan

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The adaptive ability of the algorithm, therefore, is not good enough and there is still much room for improvement. Saddami et al proposed a new binarization method using a novel local adaptive threshold to extract information from nonuniform illumination images [19]. The new local threshold is an adaptive mean value.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Binarization of QR Code Images for Fast Automatic Sorting in Warehouse Systems

Rong-jun

et al. 2019

Sensors

View full text Add to dashboard Cite

As the fundamental element of the Internet of Things, the QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce and logistics, we mainly focus on how to identify QR codes quickly and accurately. An adaptive binarization approach is proposed to solve the problem of uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, we adaptively select the block window of the QR code for robust binarization under uneven illumination. The proposed method can eliminate the impact of uneven illumination of QR codes effectively whilst meeting the real-time needs in the automatic warehouse sorting. Experimental results have demonstrated the superiority of the proposed approach when benchmarked with several state-of-the-art methods.

show abstract

“…Here, the digitalization may generate additional, frequently heavy noise on the document. Inherently, most degraded ancient documents contain multiple degradation types within a single document [ 5 ] and additional digitalization noise, which can lead to the failure of simple image analysis.…”

Section: Introductionmentioning

confidence: 99%

DCNet: Noise-Robust Convolutional Neural Networks for Degradation Classification on Ancient Documents

2021

Self Cite

View full text Add to dashboard Cite

Analysis of degraded ancient documents is challenging due to the severity and combination of degradation present in a single image. Ancient documents also suffer from additional noise during the digitalization process, particularly when digitalization is done using low-specification devices and/or under poor illumination conditions. The noises over the degraded ancient documents certainly cause a troublesome document analysis. In this paper, we propose a new noise-robust convolutional neural network (CNN) architecture for degradation classification of noisy ancient documents, which is called a degradation classification network (DCNet). DCNet was constructed based on the ResNet101, MobileNetV2, and ShuffleNet architectures. Furthermore, we propose a new self-transition layer following DCNet. We trained the DCNet using (1) noise-free document images and (2) heavy-noise (zero mean Gaussian noise (ZMGN) and speckle) document images. Then, we tested the resulted models with document images containing different levels of ZMGN and speckle noise. We compared our results to three CNN benchmarking architectures, namely MobileNet, ShuffleNet, and ResNet101. In general, the proposed architecture performed better than MobileNet, ShuffleNet, ResNet101, and conventional machine learning (support vector machine and random forest), particularly for documents with heavy noise.

show abstract

Effective and fast binarization method for combined degradation on ancient documents

Cited by 19 publications

References 24 publications

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Advancing OCR Accuracy in Image-to-LaTeX Conversion—A Critical and Creative Exploration

Adaptive Binarization of QR Code Images for Fast Automatic Sorting in Warehouse Systems

DCNet: Noise-Robust Convolutional Neural Networks for Degradation Classification on Ancient Documents

Contact Info

Product

Resources

About