Table structure understanding and its performance evaluation

Wang, Yalin; Phillips, Ihsin T.; Haralick, Robert M.

doi:10.1016/j.patcog.2004.01.012

Cited by 71 publications

(14 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T-Recs [11] was one of the earliest works to extract tabular data based on clustering of given word segments and overlap of the text inside the table. Y. Wang et al [12] estimates probabilities from geometric measurements made on the various entities in a given document.…”

Section: Related Workmentioning

confidence: 99%

TableNet: Deep Learning Model for End-to-end Table Detection and Tabular Data Extraction from Scanned Document Images

Paliwal

Vishwanath²,

Rahul³

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

143

View full text Add to dashboard Cite

With the widespread use of mobile phones and scanners to photograph and upload documents, the need for extracting the information trapped in unstructured document images such as retail receipts, insurance claim forms and financial invoices is becoming more acute. A major hurdle to this objective is that these images often contain information in the form of tables and extracting data from tabular sub-images presents a unique set of challenges. This includes accurate detection of the tabular region within an image, and subsequently detecting and extracting information from the rows and columns of the detected table. While some progress has been made in table detection, extracting the table contents is still a challenge since this involves more fine grained table structure(rows & columns) recognition. Prior approaches have attempted to solve the table detection and structure recognition problems independently using two separate models. In this paper, we propose TableNet: a novel end-toend deep learning model for both table detection and structure recognition. The model exploits the interdependence between the twin tasks of table detection and table structure recognition to segment out the table and column regions. This is followed by semantic rule-based row extraction from the identified tabular sub-regions. The proposed model and extraction approach was evaluated on the publicly available ICDAR 2013 and Marmot Table datasets obtaining state of the art results. Additionally, we demonstrate that feeding additional semantic features further improves model performance and that the model exhibits transfer learning across datasets. Another contribution of this paper is to provide additional table structure annotations for the Marmot data, which currently only has annotations for table detection.

show abstract

Section: Related Workmentioning

confidence: 99%

TableNet: Deep Learning Model for End-to-end Table Detection and Tabular Data Extraction from Scanned Document Images

Paliwal

Vishwanath²,

Rahul³

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

143

View full text Add to dashboard Cite

show abstract

“…Li et al [24] analyzed error types that occurred during table recognition, and proposed the overlapping areas between the detected table area and reference table area as an evaluation metric. Wang et al [25] proposed the ratio of intersection between detected table area and reference table area to the ratio of these two tables, respectively. Kasar et al [26] proposed area precision and area recall.…”

Section: Table-recognition Evaluation Metricmentioning

confidence: 99%

Table Recognition for Sensitive Data Perception in an IoT Vision Environment

et al. 2019

View full text Add to dashboard Cite

Internet of Things (IoT) technology allows us to measure, compute, and decide about the physical world around us in a quantitative and intelligent way. It makes all kinds of intelligent IoT devices popular. We are continually perceived and recorded by intelligent IoT devices, especially vision devices such as cameras and mobile phones. However, a series of security issues have arisen in recent years. Sensitive data leakage is the most typical and harmful one. Whether we are just browsing files unintentionally in sight of high-definition (HD) security cameras, or internal ghosts are using mobile phones to photograph secret files, it causes sensitive data to be captured by intelligent IoT vision devices, resulting in irreparable damage. Although the risk of sensitive data diffusion can be reduced by optical character recognition (OCR)-based packet filtering, it is difficult to use it with sensitive data presented in table form. This is because table images captured by the intelligent IoT vision device face issues of perspective transformation, and interferences of circular stamps and irregular handwritten signatures. Therefore, a table-recognition algorithm based on a directional connected chain is proposed in this paper to solve the problem of identifying sensitive table data captured by intelligent IoT vision devices. First, a Directional Connected Chain (DCC) search algorithm is proposed for line detection. Then, valid line mergence and invalid line removal is performed for the searched DCCs to detect the table frame, to filter the irregular interferences. Finally, an inverse perspective transformation algorithm is used to restore the table after perspective transformation. Experiments show that our proposed algorithm can achieve accuracy of at least 92%, and filter stamp interference completely.

show abstract

“…A table is a compact and efﬁcient presentation that is commonly used in various types of documents, especially for describing statistical and relational information [14]. It enables readers to rapidly search, compare and understand facts and draw conclusions [15].…”

Section: Tables and Their Importancementioning

confidence: 99%

“…There are three major categories of table detection methodologies: predefined layout approaches [37], heuristics-based approaches [31, 32, 54, 89] and statistical approaches, as well as a mixture of both heuristic and statistical approaches [14]. Shamilian presents a predefine layout based table identification and segmentation algorithm [37].…”

Section: State Of the Art In Table Detection Extraction And Annotmentioning

confidence: 99%

“…The dataset is commonly used but, except for bounding box information of the table region, no other structure information is provided [111]. Wang et al provide a downloadable software tool package, and produced 1125 document image ground-truths, 565 table entities and 10,298 cell entities, but their dataset and ground-truth are not publicly available [14]. Fang et al [12] provide a ground-truth general dataset, and propose evaluation metrics with publicly available source code for table detection algorithms.…”

Section: State Of the Art In Table Detection Extraction And Annotmentioning

confidence: 99%

See 1 more Smart Citation

On methods and tools of table detection, extraction and annotation in PDF documents

Khusro

Latif

Ullah

2014

Journal of Information Science

View full text Add to dashboard Cite

Table detection, extraction and annotation have been an important research problem for years. To handle this issue, different approaches have been designed for different types of documents. Among these PDF is a widely used format for preserving and presenting different types of documents. We investigate the state of the art in table detection, extraction and annotation in PDF documents. Because of varying table structural anatomy, the state of the art in table-related research enumerates a number of approaches that are critically and analytically investigated for identifying their strengths and limitations as well as for making recommendations for further improvement. An evaluation framework is contributed that compares different information extraction tools that may be used in table detection, extraction and annotation. We found very limited attention towards these aspects in books, especially books in PDF format. There is no searching solution that can find books having tables that are semantically related to a table in a given book.

show abstract

Table structure understanding and its performance evaluation

Cited by 71 publications

References 19 publications

TableNet: Deep Learning Model for End-to-end Table Detection and Tabular Data Extraction from Scanned Document Images

TableNet: Deep Learning Model for End-to-end Table Detection and Tabular Data Extraction from Scanned Document Images

Table Recognition for Sensitive Data Perception in an IoT Vision Environment

On methods and tools of table detection, extraction and annotation in PDF documents

Contact Info

Product

Resources

About