Title: Convolutional neural network based chart image classification
Authors: Amara, Jihen
Kaur, Pawandeep
Owonibi, Michael
Bouaziz, Bassem
Citation: WSCG 2017: poster papers proceedings: 25th International Conference in Central Europe on Computer Graphics, Visualization and Computer Visionin co-operation with EUROGRAPHICS Association, p. 83-88.
Issue Date: 2017
Publisher: Václav Skala - UNION Agency
Document type: konferenční příspěvek
URI: wscg.zcu.cz/WSCG2017/!!_CSRN-2703.pdf
ISBN: 978-80-86943-46-6
ISSN: 2464-4617
Keywords: klasifikace grafu obrázku;vizualizace dat;hluboké učení;anotace datasetu
Keywords in different language: chart image classification;data visualization;deep learning;dataset annotation
Abstract: Charts are frequently embedded objects in digital documents and are used to convey a clear analysis of research results or commercial data trends. These charts are created through different means and may be represented by a variety of patterns such as column charts, line charts and pie charts. Chart recognition is as important as text recognition to automatically comprehend the knowledge within digital document. Chart recognition consists on identifying the chart type and decoding its visual contents into computer understandable values. Previous work in chart image identification has relied on hand crafted features which often fails when dealing with a large amount of data that could contain significant varieties and less common char types. Hence, as a first step towards this goal, in this paper we propose to use a deep learning-based approach that automates the feature extraction step. We present an improved version of the LeNet [LeCu 89] convolutional neural network architecture for chart image classification. We derive 11 classes of visualization (Scatter Plot, Column Chart, etc.) which we use to annotate 3377 chart images. Results show the efficiency of our proposed method with 89.5 % of accuracy rate.
Rights: © Václav Skala - Union Agency
Appears in Collections:WSCG 2017: Poster Papers Proceedings

Files in This Item:
File Description SizeFormat 
Amara.pdfPlný text909,72 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/29617

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.