Evaluation of Shallow Convolutional Neural Network in Open-World Chart Image Classification

Data s role is pivotal in the era of internet technologies, but unstructured data poses comprehension challenges. Data visualizations like charts have emerged as crucial tools for condensing complex information. Classifying charts and applying various processing techniques are vital to interpreting...

Full description

Saved in:
Bibliographic Details
Published inInformatica (Ljubljana) Vol. 48; no. 6; pp. 185 - 198
Main Authors Bajić, Filip, Habijan, Marija, Nenadić, Krešimir
Format Journal Article
LanguageEnglish
Published Ljubljana Slovenian Society Informatika / Slovensko drustvo Informatika 01.03.2024
Subjects
Accuracy
Algorithms
Artificial neural networks
Charts
Classification
Comparative analysis
Datasets
Image classification
Internet
Neural networks
Support vector machines
Unstructured data
Visual impairment
Visualization
Online AccessGet full text

Cover

More Information
Summary:Data s role is pivotal in the era of internet technologies, but unstructured data poses comprehension challenges. Data visualizations like charts have emerged as crucial tools for condensing complex information. Classifying charts and applying various processing techniques are vital to interpreting visual data. Traditional chart image classification methods rely on predefined rules and have limited accuracy. The advent of support vector machines (SVMs) and convolutional neural networks (CNNs) significantly improved the accuracy of these methods. This research evaluates our previously introduced Shallow convolutional neural network (SCNN) architecture for chart image classification, comprising four convolutional layers, two max-pooling layers, and one fully-connected layer. The network achieves state-of-the-art results, requiring smaller datasets and reduced computational resources. When two networks are combined into Siamese SCNN (SSCNN), emphasizing generalization, it achieves high accuracy with small datasets and excels in open-set classification. The evaluation process encompasses the utilization of six publicly available datasets.
ISSN:0350-5596
1854-3871
DOI:10.31449/inf.v48i6.5660