An analysis of the transition proportion for binarization in handwritten historical documents

Ramírez-Ortegón, Marte A.; Ramírez-Ramírez, L. Leticia; Märgner, Volker; Messaoud, Ines Ben; Cuevas, Erik; Rojas, Raúl

doi:10.1016/j.patcog.2014.02.003

Cited by 11 publications

(9 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Eleven binarization methods are used for the evaluation of the proposed method: Abutaleb's method [2], Gato's method [36], Howe's method (winner of H-DIBCO'12) [20], Lu et al's method (winner of DIBCO'09) [15], Hedjam's method [31], GridSauvola's (GSauv) method [33] and Otsu's method [1], Tsai's method [37], Wolf's method (5th rank in DIBCO'09) [38], Ramirez-Ortegnon's (RO in brief) method [39], and Lelore's method [40]. Figure 9 shows the results of various binarization methods of the image shown in Figure 6 using different color-to-gray conversion methods.…”

Section: B Evaluation Of the Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Influence of Color-to-Gray Conversion on the Performance of Document Image Binarization: Toward a Novel Optimization Problem

Hedjam

Nafchi

Kalácska

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This paper presents a novel preprocessing method of color-to-gray document image conversion. In contrast to the conventional methods designed for natural images that aim to preserve the contrast between different classes in the converted gray image, the proposed conversion method reduces as much as possible the contrast (i.e., intensity variance) within the text class. It is based on learning a linear filter from a predefined data set of text and background pixels that: 1) when applied to background pixels, minimizes the output response and 2) when applied to text pixels, maximizes the output response, while minimizing the intensity variance within the text class. Our proposed method (called learning-based color-to-gray) is conceived to be used as preprocessing for document image binarization. A data set of 46 historical document images is created and used to evaluate subjectively and objectively the proposed method. The method demonstrates drastically its effectiveness and impact on the performance of state-of-the-art binarization methods. Four other Web-based image data sets are created to evaluate the scalability of the proposed method.

show abstract

Section: B Evaluation Of the Proposed Methodsmentioning

confidence: 99%

“…6. 1) Lelore [40]; 2) RO [39]; 3) Howe [20]; 4) Lu et al [15]; 5) Gatos [36]; 6) Wolf [38]; 7) Hedjam [31]; 8) Grid-Sauvola [33] ; 9) Tsai [37]; 10) Abutaleb [2]; 11) Otsu [1]. Due to lack of space the binarization of the gray image of Gimp is not included.…”

Section: Scalability and Stability Of The Methodsmentioning

confidence: 99%

Influence of Color-to-Gray Conversion on the Performance of Document Image Binarization: Toward a Novel Optimization Problem

Hedjam

Nafchi

Kalácska

et al. 2015

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The idea of a transition pixel was introduced in [133] and later expanded upon [134,137]. These works define a…”

Section: Other Statistical Approachesmentioning

confidence: 99%

Historical Document Image Binarization: A Review

Tensmeyer

Martinez

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

This review provides a comprehensive view of the field of historical document image binarization with a focus on the contributions made in the last decade. After the introduction of a standard benchmark dataset with the 2009 Document Image Binarization Contest, research in the field accelerated. Besides the standard methods for image thresholding, preprocessing, and post-processing, we review the literature on methods such as statistical models, pixel classification with learning algorithms, and parameter tuning. In addition to reviewing binarization algorithms, we discuss the available public datasets and evaluation metrics, including those that require pixel-level ground truth and those that do not. We conclude with recommendations for future work.

show abstract

“…In the computation of the kCF and kFS, a binary method is needed to obtain the binary document image and compute contours and skeleton lines of the ink traces. Although several binarization methods have been proposed in the literature, such as [49][50][51][52][53], we apply the simple and efficient Otsu threshold algorithm [54] in our experiments, followed by the guided filter [55] to remove noise and make contours smooth. Each contour fragment of kCF is resampled to contain 100 points and the feature dimension is 100 Â 2 ¼ 200.…”

Section: Experimental Settingsmentioning

confidence: 99%