This page (revision-61) was last changed on 19-Sep-2022 11:15 by Arnab Ghosh Chowdhury

This page was created on 10-May-2022 15:30 by Arnab Ghosh Chowdhury

Only authorized users are allowed to rename pages.

Only authorized users are allowed to delete pages.

Page revision history

Version Date Modified Size Author Changes ... Change note
61 19-Sep-2022 11:15 5 KB Arnab Ghosh Chowdhury to previous

Page References

Incoming links Outgoing links
Data Extractor
Data Extractor

Version management

Difference between version and

At line 1 changed one line
(Please insert an screenshot of the Tool)
[{Image src='Data Extractor/MDE_1_Home.png' width=600}]
At line 3 changed one line
__%%( color: #003399; font-size: 18px;)Type of tool: Web application
__%%( color: #003399; font-size: 30px;)Matrix Data Extractor:__
At line 5 changed one line
__%%( color: #003399; font-size: 18px;)Required skills: __
Tabular data extraction from PDF documents is critical task due to diverse PDF templates and Table templates. Some open-source tools do not support all possible types of PDF templates for tabular data extraction. A computer vision based document table detection approach is considered along with Camelot tool to extract tabular information from PDF documents. A post-processing work is necessary after tabular data extraction.
At line 7 removed one line
- Elementary User: No programming
At line 9 changed one line
- Advanced User: Python, Basic Deep Learning (PyTorch)
__%%( color: #003399; font-size: 16px;)Type of tool:__ Web application to be deployed on your computer that supports Linux operating system.
At line 11 changed one line
__%%( color: #003399; font-size: 18px;)Short description of the tool: __
__%%( color: #003399; font-size: 16px;)Short description of the tool: __ Extract tabular data and textual data from product technical datasheets (PDF documents)
At line 13 changed one line
- Detailed description: [Data Extractor/MatrixDataExtractor_UserGuide.pdf]
Matrix Data Extractor (MDE) is a web-based application, which can be deployed on your computer. It identifies document table regions on PDF documents using Computer Vision based Deep Learning, especially Transfer Learning and Object Detection algorithm. It extracts all textual data into text files by applying Optical Character Recognition (OCR) and also extracts tabular data separately in excel files using Camelot python package. It supports to transfer manufacturer names and corresponding technical datasheets names (or PDF filenames) to MongoDB database table for further processing.
At line 15 removed one line
__%%( color: #003399; font-size: 18px;)Disclaimer:__
At line 17 changed one line
Any support to provide table detection model will not be provided unfortunately after project completion. The accuracy of table detection model depends on various factors such as volume, variety of annotated datasets, hyperparameters of model. You can do your experiment to get better accuracy of your table detection model.
\\__%%( color: #003399; font-size: 16px;)Required skills: __\\
- Linux OS (operating system)\\
- Elementary (Normal) User: No programming\\
- Advanced User: Python, Basic Deep Learning (PyTorch), Shell scripting\\
At line 20 added 6 lines
\\__%%( color: #003399; font-size: 16px;)Required programs %%( color: #003000; font-size: 14px;)(step-by-step guide and links provided in GitHub and user guideline blow): __
\\- Python
\\- Shell script
\\- Anaconda
\\- Linux
\\- Code from GitHub ([https://github.com/cslab-hub/MatrixDataExtractor])
At line 20 changed one line
__%%( color: #003399; font-size: 18px;)How to use/download/access it:__
__%%( color: #003399; font-size: 16px;)Disclaimer:__\\
Any support to provide table detection model will not be provided unfortunately after project completion. The accuracy of table detection model depends on various factors such as volume, variety of annotated datasets, hyperparameters of model. You can do your experiment to get better accuracy of your table detection model. To get table detection model weight on Di-Plast dataset, you can request to Semantic Information Systems Research Group, Osnabrueck University, Osnabrueck, Germany ( [https://www.informatik.uni-osnabrueck.de/arbeitsgruppen/semantische_informationssysteme.html|https://www.informatik.uni-osnabrueck.de/arbeitsgruppen/semantische_informationssysteme.html] ).
At line 22 removed 2 lines
Get the GitHub [https://github.com/cslab-hub/MatrixDataExtractor], copy
the code into your computer, prepare your annotated dataset and start using it\\
At line 31 added 9 lines
__%%( color: #003399; font-size: 16px;)Screenshots:__
%%carousel
[Data Extractor/MDE_Home.png]
[Data Extractor/MDE_SyncData.png]
[Data Extractor/MDE_DataInfoExt_1.png]
[Data Extractor/MDE_DataInfoExt_2.png]
[Data Extractor/MDE_DataInfoExt_3.png]
[Data Extractor/MDE_TableDataExt.png]
/%
At line 26 changed one line
_%%( color: #003399; font-size: 18px;)Use case/problem:__
\\__%%( color: #003399; font-size: 24px;)This tool supports you to:__\\
\\ - Extract textual and tabular information from PDF documents.
\\ - ⚠️ For brief overview about the tool, we recommend to open and save the presentation before proceeding: [Data Extractor/Di-Plast_MDE_UI.pdf]
At line 28 changed one line
Tabular data extraction from product technical datasheets.
\\__%%( color: #003399; font-size: 18x;)Example use case:__\\
\\ - Open-source document table detection tools are not suitable enough to extract tabular information from PDF documents by considering all possible document templates and table templates. Due to diverse document templates and table templates, computer vision and transfer learning based document table detection emerged significantly. This tool helps to extract textual and tabular data (in excel files) from your domain specific dataset. The extracted data can be used in Big Data technologies and Natural Language Processing (NLP).
At line 30 changed one line
__%%( color: #003399; font-size: 18px;)__Description of the problem the tools solves__:__
\\__%%( color: #003399; font-size: 24px;)Tool guideline and access: __
\\ - ⚠️ We recommend to open and save the user guideline before proceeding: [Data Extractor/MatrixDataExtractor_UserGuide.pdf]
\\ - Get GitHub [https://github.com/cslab-hub/MatrixDataExtractor], copy code into your computer, prepare your annotated dataset, build or request about table detection model weight and model description file, and start using it\\
At line 32 removed one line
__[[General] + [[Tool-specific]__
At line 34 removed 21 lines
__%%( color: #003399; font-size: 18px;)__Contact person of the tool__: A
__%%( color: #003399; font-size: 18px;)Related tools:__
- Analyse and Visualize your process data with data analytics -> [Data Analytics]
- Get guidance to set up a working data infrastucture -> [Data Infrastructure Wiki]
- Find the right sensor to survey your process -> [Sensor Tool]
- Improve internal information and material flow -> [VSM]
- Match material requirements with material properties -> [Matrix]
!Tool Description
Matrix Data Extractor (MDE) is a web-based application that identifies document table regions on PDF documents using Computer Vision based Deep Learning algorithm and extracts data to text files by applying Optical Character Recognition (OCR). It supports to transfer extracted data to MongoDB database tables. A search functionality is also provided to retrieve data on user interface based on Keyword matching (e.g. Manufacturer Name, Technical Datasheet Name, Keyword for Table Data).
! Guidelines
Before getting started, please take a look at [Data Extractor/MatrixDataExtractor_UserGuide.pdf] and make yourself familiar with how to use the tool.
At line 62 added 15 lines
\\__%%( color: #003399; font-size: 16px;)Contact person of the tool: __
Arnab Ghosh Chowdhury, [mailto:arnab.ghosh.chowdhury@uni-osnabrueck.de] form the Osnabrueck University.
__%%( color: #003399; font-size: 16px;) Before applying this tool:__
\\We recommend also taking a look at the following Di-Plast tools below. They can help you to gather necessary information and data, help to better prepare your data and continue working with it afterwards:
\\--> Improve internal information and material flow -> [VSM]
\\--> Get guidance to set up a working data infrastructure -> [Data Infrastructure Wiki]
\\--> Find the right sensor to survey your process -> [Sensor Tool]
\\-->Analyse and Visualize your process data with data analytics -> [Data Analytics]
\\-->Get important insights in enhancing your data understanding
-> [Exploratory Pattern Analytics]
\\
\\__%%( color: #003399; font-size: 16px;)After applying this tool:__\\
-->Match material requirements with material properties -> [Matrix]
This page (revision-61) was last changed on 19-Sep-2022 11:15 by Arnab Ghosh ChowdhuryTop