Handwritten Text Lines Segmentation Using Two Column Projection

Babczyński, Tomasz; Ptak, Roman

doi:10.1007/978-3-030-48256-5_2

Cited by 2 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tokens cast their votes within their local vicinity, either on other tokens through sparse voting, or across all positions via dense voting. 1 The "size" and "shape" refer to the graphical representation as an ellipse. b) Analyzing voting strength: In the Tensor Voting method, the intensity of the vote is determined through a consideration of both spatial separation and the angular disparity between tensors.…”

Section: A An Overview Of Tensor Voting Methods In Two-dimensional Spacementioning

confidence: 99%

“…Both older publications like [7], [8] and newer papers like [9], [10] employ these methods. Some algorithms also utilize piece-wise projection profiles, as seen in [11], [12], which can effectively handle instances of overlapping or slanted lines in handwritten documents.…”

Section: Background Researchmentioning

confidence: 99%

“…The complete code of the algorithm and evaluation procedure can be found in a public repository [43].…”

Section: Algorithm 1 Summary Of the Algorithmmentioning

confidence: 99%

“…T HIS paper is an extended version of the [1] publication, offering a more comprehensive literature review and presenting additional experimental results.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Direct Tensor Voting in line segmentation of handwritten documents

Babczyński,

Ptak

2024

International Journal of Electronics and Telecommunications

View full text Add to dashboard Cite

In the vast archives and libraries of the world, countless historical documents are tucked away, often difficult to access. Thankfully, the digitization process has made it easier to view these invaluable records. However, simply digitizing them is not enough – the real challenge lies in making them searchable and computer-readable. Many of these documents were handwritten, which means they need to undergo handwriting recognition. The first step in this process is to divide the document into lines. This article introduces a solution to this problem using tensor voting. The algorithm starts by conducting voting on the binary image itself. Then, using the local maxima found in the resulting tensor field, the lines of text are precisely tracked and labeled. To ensure its effectiveness, the algorithm’s performance was tested on the data-set delivered by the organizers of the ICDAR 2009 competition and evaluated using the criteria from this contest.

show abstract

Section: A An Overview Of Tensor Voting Methods In Two-dimensional Spacementioning

confidence: 99%