Table Detection Using Deep Learning

Gilani, Azka; Qasim, Shah Rukh; Malik, Imran; Shafait, Faisal

doi:10.1109/icdar.2017.131

Cited by 161 publications

(122 citation statements)

References 17 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…In [9], Gilani et al present a deep learning-based method for table detection in document images. The proposed method consists of two major modules: image transformation and table detection.…”

Section: Text-analysis Methodsmentioning

confidence: 99%

“…However, several performance measures have been used by researchers in the literature for evaluating table detection. These measures vary (as discussed in [34] and [9]) from simple precision-and recall-based measures to more sophisticated measures for benchmarking complete table structure-extraction algorithms.…”

Section: Table-detection Measuresmentioning

confidence: 99%

“…These measures are correct detections, partial detections, over-segmented tables, under-segmented tables, missed tables, and false-positive detections in addition to recall, precision, and F1 score. These measures have been used by several researchers (for example, in [9] and [39]).…”

Section: Table-detection Measuresmentioning

confidence: 99%

See 2 more Smart Citations

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: Text-analysis Methodsmentioning

confidence: 99%

Section: Table-detection Measuresmentioning

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

show abstract

“…In [1,2], efforts are made to apply DL-based methods for table localization and detection from image or scanned documents. In [1,2], a framework for table detection and recognition is proposed. For this work, Faster-RCNN is used as a backbone network.…”

Section: Sn Computer Sciencementioning

confidence: 99%

“…For this work, Faster-RCNN is used as a backbone network. Method proposed in [1,2] handles the unavailability of large training data by using transfer learning approach with very carefully tuned parameters [2] also uses data augmentation to handle annotated data problem. The results of the method presented in [2] are validated on publicly available UNLV data set [23] and [1] on ICDAR 2013 data.…”

Section: Sn Computer Sciencementioning

confidence: 99%

Weakly Supervised Learning-based Table Detection

Gurav

Nene

2020

SN COMPUT. SCI.

View full text Add to dashboard Cite

CNN has given the state-of-the-art results in computer vision and natural language processing (NLP) domain problems. This has motivated researchers to use deep learning-based techniques for document layout analysis. Due to recent advances in communication and in information technology, methods of data storage, extraction and processing are rapidly evolving. In an information space, there is a large volume of digital documents (DD) already available, and more DD is created continuously. The DD can be natural images, scanned documents, mails, books, archives, etc. Processing, extraction and understanding of relevant information from these DD have prime business importance. Information in DD is present in the form of tables, text, figure, images, diagram, etc. Document images (DI) are DD which are present in the form of images. It is especially office, scanned documents. Recent progress in artificial intelligence has created a growing expectation for automation of data extraction from DD. Tables are frequently present in DI. There is a desperate need to handle tabular information present in DI; otherwise, this information will remain unused and there is high possibility that it will be lost. In this work, we present weakly supervised learning-based approach to detect and recognize the location of the table. The novelty of our work is that it did not require bounding box annotations for table detection. Application of our technique on ICDAR 2013 test data has demonstrated encouraging results.

show abstract

A Saliency-Based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

Kavasidis

Pino

Palazzo

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Deep Convolutional Neural Networks (DCNNs) have recently been applied successfully to a variety of vision and multimedia tasks, thus driving development of novel solutions in several application domains. Document analysis is a particularly promising area for DCNNs: indeed, the number of available digital documents has reached unprecedented levels, and humans are no longer able to discover and retrieve all the information contained in these documents without the help of automation. Under this scenario, DCNNs offers a viable solution to automate the information extraction process from digital documents. Within the realm of information extraction from documents, detection of tables and charts is particularly needed as they contain a visual summary of the most valuable information contained in a document. For a complete automation of visual information extraction process from tables and charts, it is necessary to develop techniques that localize them and identify precisely their boundaries. In this paper we aim at solving the table/chart detection task through an approach that combines deep convolutional neural networks, graphical models and saliency concepts. In particular, we propose a saliency-based fully-convolutional neural network performing multi-scale reasoning on visual cues followed by a fully-connected conditional random field (CRF) for localizing tables and charts in digital/digitized documents. Performance analysis carried out on an extended version of ICDAR 2013 (with annotated charts as well as tables) shows that our approach yields promising results, outperforming existing models.

show abstract

Table Detection Using Deep Learning

Cited by 161 publications

References 17 publications

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

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

Weakly Supervised Learning-based Table Detection

A Saliency-Based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

Contact Info

Product

Resources

About