A mixture model using Random Rotation Bounding Box to detect table region in document image

Tran, Tuan Anh; Tran, Hong Tai; Na, In Seop; Lee, Guee Sang; Yang, Hyung Jeong; Kim, Sung Hyun

doi:10.1016/j.jvcir.2016.05.023

Cited by 15 publications

(11 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to [39], table-detection methods can be divided into two main classes: non-text-analysis methods (using ruling lines) and text-analysis methods. Non-textanalysis methods were the first methods of table detection proposed in the literature.…”

Section: Previous Workmentioning

confidence: 99%

“…They detect the location of a table by analyzing the ruling lines of the table, and they usually require a phase of preprocessing (like skew correction). The disadvantage of these methods is that they are only effective for some individual tables that are comprised of full horizontal and vertical ruling lines [39]. Text-analysis methods, on the other hand, do not require the presence of any guideline, and they use text information to analyze and recognize the table regions.…”

Section: Previous Workmentioning

confidence: 99%

See 1 more Smart Citation

Extraction of Scores and Average From Algerian High-School Degree Transcripts

Kefali¹,

Drabsia²,

Sari³

et al. 2020

csci

View full text Add to dashboard Cite

A system for extracting scores and average from Algerian High School Degree Transcripts is proposed. The system extracts the scores and the average based on the localization of the tables gathering this information and it consists of several stages. After preprocessing, the system locates the tables using ruling-lines information as well as other text information. Therefore, the adopted localization approach can work even in the absence of certain ruling-lines or the erasure and discontinuity of lines. After that, the localized tables are segmented into columns and the columns into information cells. Finally, cells labeling is done based on the prior knowledge of the tables structure allowing to identify the scores and the average. Experiments have been conducted on a local dataset in order to evaluate the performances of our system and compare it with three public systems at three levels, and the obtained results show the effectiveness of our system.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Previous Workmentioning

confidence: 99%

Extraction of Scores and Average From Algerian High-School Degree Transcripts

Kefali¹,

Drabsia²,

Sari³

et al. 2020

csci

View full text Add to dashboard Cite

show abstract

“…Tables are one of the most common objects that can be found in multiple classes of documents throughout the history from scientific journals and newspapers to forms and invoices. Tables are used to summarize the correlational data and present them in an ordered, meaningful and compact manner (Tran et al, 2016).…”

Section: What Is a Table?mentioning

confidence: 99%

“…Not all the tables in document images include frames and separator lines. In this sense, we can classify tables into two main classes according to their framing composition: ruling-line tables (RL-Ts) and non-ruling-line tables (NRL-Ts) (Tran et al, 2016). Figure 3.4 illustrates this categorization in more detail.…”

Section: Table Frames and Separator Linesmentioning

confidence: 99%

Visual information retrieval from historical document images

Zhalehpour

Arabnejad

Wellmon

et al. 2019

Journal of Cultural Heritage

View full text Add to dashboard Cite

“…Based on properties of non-text elements, they are classified into negative-text region, line, table, separator, and image. The system also contains a robust table detection method which was introduced by Tran et al [20] in 2016.…”

Section: Text and Non-text Classification -mentioning

confidence: 99%