thumbnail

Automatic Single Page-based Algorithms for Medieval Manuscript Analysis

Ying Yang, Ruggero Pintus, Enrico Gobbetti, and Holly Rushmeier

2017

Abstract

We propose three automatic algorithms for analyzing digitized medieval manuscripts: text block computation, text line segmentation and special component extraction, by taking advantage of previous clustering algorithms and a template matching technique. These three methods are completely automatic, so that no user intervention or input is required to make them work. Moreover, they are all per-page based; that is, unlike some prior methods–which need a set of pages from the same manuscript for training purposes–they are able to analyze a single page without requiring any additional pages for input, eliminating the need for training on additional pages with similar layout. We extensively evaluated the algorithms on 1771 images of pages of 6 different publicly available historical manuscripts, which differ significantly from each other in terms of layout structure, acquisition resolution, and writing style, etc. The experimental results indicate that they are able to achieve very satisfactory performance, i.e., the average precision and recall values obtained by the text block computation method can reach as high as 98\% and 99\%, respectively.

Reference and download information

Ying Yang, Ruggero Pintus, Enrico Gobbetti, and Holly Rushmeier. Automatic Single Page-based Algorithms for Medieval Manuscript Analysis. ACM Journal on Computing and Cultural Heritage, 10(2): 9:1-9:22, 2017. http://dx.doi.org/10.1145/2996469.

Related multimedia productions

Bibtex citation record

@Article{Yang:2017:3SA,
    author = {Ying Yang and Ruggero Pintus and Enrico Gobbetti and Holly Rushmeier},
    title = {Automatic Single Page-based Algorithms for Medieval Manuscript Analysis},
    journal = {ACM Journal on Computing and Cultural Heritage},
    volume = {10},
    number = {2},
    pages = {9:1--9:22},
    year = {2017},
    abstract = { We propose three automatic algorithms for analyzing digitized medieval manuscripts: text block computation, text line segmentation and special component extraction, by taking advantage of previous clustering algorithms and a template matching technique. These three methods are completely automatic, so that no user intervention or input is required to make them work. Moreover, they are all per-page based; that is, unlike some prior methods–which need a set of pages from the same manuscript for training purposes–they are able to analyze a single page without requiring any additional pages for input, eliminating the need for training on additional pages with similar layout. We extensively evaluated the algorithms on 1771 images of pages of 6 different publicly available historical manuscripts, which differ significantly from each other in terms of layout structure, acquisition resolution, and writing style, etc. The experimental results indicate that they are able to achieve very satisfactory performance, i.e., the average precision and recall values obtained by the text block computation method can reach as high as 98\% and 99\%, respectively.},
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Yang:2017:3SA'},
}

thumbnail

A 3D Steganalytic Algorithm and Steganalysis-Resistant Watermarking

Ying Yang, Ruggero Pintus, Holly Rushmeier, and Ioannis Ivrissimtzis

February 2017

Abstract

We propose a simple yet efficient steganalytic algorithm for watermarks embedded by two state-of-the-art 3D watermarking algorithms by Cho et al. The main observation is that while in a clean model the means/variances of Cho et al.’s normalized histogram bins are expected to follow a Gaussian distribution, in a marked model their distribution will be bimodal. The proposed algorithm estimates the number of bins through an exhaustive search and then the presence of a watermark is decided by a tailor made normality test or a t-test. We also propose a modification of Cho et al.’s watermarking algorithms with the watermark embedded by changing the histogram of the radial coordinates of the vertices. Rather than targeting a continuous statistics such as the mean or variance of the values in a bin, the proposed watermarking modifies a discrete statistic, which here is the height of the histogram bin, to achieve watermark embedding. Experimental results demonstrate that the modified algorithm offers not only better resistance against the steganalytic attack we developed, but also an improved robustness/capacity trade-off.

Reference and download information

Ying Yang, Ruggero Pintus, Holly Rushmeier, and Ioannis Ivrissimtzis. A 3D Steganalytic Algorithm and Steganalysis-Resistant Watermarking. IEEE Transactions on Visualization and Computer Graphics, 23(2): 1002-1013, February 2017. http://dx.doi.org/10.1109/TVCG.2016.2525771.

Related multimedia productions

Bibtex citation record

@Article{Yang:2017:3SA,
    author = {Ying Yang and Ruggero Pintus and Holly Rushmeier and Ioannis Ivrissimtzis},
    title = {A {3D} Steganalytic Algorithm and Steganalysis-Resistant Watermarking},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    volume = {23},
    number = {2},
    pages = {1002--1013},
    month = {February},
    year = {2017},
    abstract = { We propose a simple yet efficient steganalytic algorithm for watermarks embedded by two state-of-the-art 3D watermarking algorithms by Cho et al. The main observation is that while in a clean model the means/variances of Cho et al.’s normalized histogram bins are expected to follow a Gaussian distribution, in a marked model their distribution will be bimodal. The proposed algorithm estimates the number of bins through an exhaustive search and then the presence of a watermark is decided by a tailor made normality test or a t-test. We also propose a modification of Cho et al.’s watermarking algorithms with the watermark embedded by changing the histogram of the radial coordinates of the vertices. Rather than targeting a continuous statistics such as the mean or variance of the values in a bin, the proposed watermarking modifies a discrete statistic, which here is the height of the histogram bin, to achieve watermark embedding. Experimental results demonstrate that the modified algorithm offers not only better resistance against the steganalytic attack we developed, but also an improved robustness/capacity trade-off. },
    url = {http://vic.crs4.it/vic/cgi-bin/bib-page.cgi?id='Yang:2017:3SA'},
}