Hybrid page segmentation using multilevel homogeneity structure

Tran, Tuan Anh; Na, In Seop; Kim, Soo-Hyung

doi:10.1145/2701126.2701138

Cited by 13 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Top-down approaches could instead provide more efficiency in computation, but only limited to processing specific types, like documents with a manhattan-based layout. Hence, hybrid methods [38,40] were adopted in literature which could combine both top-down and bottom-up cues to generate better results. Prior to deep learning era, rule-based segmentation techniques [7,10,37] were also used profoundly to solve the table detection problem.…”

Section: Heuristic Rule-based Document Layout Analysismentioning

confidence: 99%

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

Biswas¹,

Banerjee²,

Lladós³

et al. 2022

Preprint

View full text Add to dashboard Cite

Understanding documents with rich layouts is an essential step towards information extraction. Business intelligence processes often require the extraction of useful semantic content from documents at a large scale for subsequent decision-making tasks. In this context, instance-level segmentation of different document objects(title, sections, figures, tables and so on) has emerged as an interesting problem for the document layout analysis community. To advance the research in this direction, we present a transformer-based model for end-to-end segmentation of complex layouts in document images. To our knowledge, this is the first work on transformer-based document segmentation. Extensive experimentation on the PubLayNet dataset shows that our model achieved comparable or better segmentation performance than the existing state-of-the-art approaches. We hope our simple and flexible framework could serve as a promising baseline for instance-level recognition tasks in document images.

show abstract

Section: Heuristic Rule-based Document Layout Analysismentioning

confidence: 99%

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

Biswas¹,

Banerjee²,

Lladós³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Asi et al [2] came up with a multi-scale texture-based algorithm for document images where Gabor filters were applied to locate different regions and a minimization energy function was applied to segment them. Despite successes of both top-down and bottom-up strategies, there are techniques [51] that have integrated both of them to segment regions in digital documents with complex layouts.…”

Section: Traditional Document Layout Segmentationmentioning

confidence: 99%

Beyond document object detection: instance-level segmentation of complex layouts

Biswas

Riba

Lladós

et al. 2021

IJDAR

View full text Add to dashboard Cite

Information extraction is a fundamental task of many business intelligence services that entail massive document processing. Understanding a document page structure in terms of its layout provides contextual support which is helpful in the semantic interpretation of the document terms. In this paper, inspired by the progress of deep learning methodologies applied to the task of object recognition, we transfer these models to the specific case of document object detection, reformulating the traditional problem of document layout analysis. Moreover, we importantly contribute to prior arts by defining the task of instance segmentation on the document image domain. An instance segmentation paradigm is especially important in complex layouts whose contents should interact for the proper rendering of the page, i.e., the proper text wrapping around an image. Finally, we provide an extensive evaluation, both qualitative and quantitative, that demonstrates the superior performance of the proposed methodology over the current state of the art.

show abstract

“…Based on the binary image, we use the algorithm [19] to extract CC and store the coordinates. Let CCs be all the CC, CC i is the i th connected component in binary In 2015, Tran et al [21] proposed an effective method for classifying the text and non-text elements based on the multilevel classification. However, the goal of our system is the table detection where table candidates (non-text elements) are very different with text elements.…”

Section: Pre-processingmentioning

confidence: 99%

“…However, the goal of our system is the table detection where table candidates (non-text elements) are very different with text elements. Therefore, we only used the heuristic filter in [21] to determine the nontext elements for ruling line table candidate. In an addition to find the color table candidates, the CC i is classified the non-text element if CC i 's filled area is big and approximate…”

Section: Pre-processingmentioning

confidence: 99%

See 1 more Smart Citation

A hybrid method for table detection from document image

Anh

Kim

2015

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)

View full text Add to dashboard Cite

In this paper, we present a hybrid method consisting of three main stages for detecting tables in document images. Based on table structure, our system separates table into two main categories, ruling line table and nonruling line table. In the first stage, the text and non-text elements in document are classified by a heuristic filter. Then, the white space analysis is used to group the text elements into text lines, while ruling line table candidates are identified from non-text elements. In the second stage, based on the text lines, text and non-text elements, a hybrid method which consist of the alternative bottom-up and top-down approaches is implemented to find the table region candidates. In the final stage, these candidates are examined to get the table regions by analyzing text lines and spare lines. Experimental results with the document database from the ICDAR2013 table competition show that the proposed method works better than the previous ones.

show abstract

Hybrid page segmentation using multilevel homogeneity structure

Cited by 13 publications

References 24 publications

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer

Beyond document object detection: instance-level segmentation of complex layouts

A hybrid method for table detection from document image

Contact Info

Product

Resources

About