ChartFuse: a novel fusion method for chart classification using heterogeneous microstructures

Mishra, Prashant; Kumar, Santosh; Chaube, Mithilesh Kumar

doi:10.1007/s11042-020-10186-z

Cited by 8 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the complex image preprocessing, supported chart classes are usually limited to bar, pie, and line charts. The most notable publications that classify chart images based on a pixel level and graphical symbol level are image and graphic reader [ 15 ], View [ 16 ], Beagle [ 17 ], and ChartFuse [ 18 ]. In Beagle [ 17 ], the authors report average classification accuracy of 86%.…”

Section: Related Workmentioning

confidence: 99%

“…In Beagle [ 17 ], the authors report average classification accuracy of 86%. In ChartFuse [ 18 ], the authors compare different methods that work on a pixel level and propose a method that differentiates colors, textures, structural layout, and illumination details. The proposed method achieves average classification accuracy of 95–97%.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Multi-Purpose Shallow Convolutional Neural Network for Chart Images

Bajić

Orel

Habijan

2022

Sensors

View full text Add to dashboard Cite

Charts are often used for the graphical representation of tabular data. Due to their vast expansion in various fields, it is necessary to develop computer algorithms that can easily retrieve and process information from chart images in a helpful way. Convolutional neural networks (CNNs) have succeeded in various image processing and classification tasks. Nevertheless, the success of training neural networks in terms of result accuracy and computational requirements requires careful construction of the network layers’ and networks’ parameters. We propose a novel Shallow Convolutional Neural Network (SCNN) architecture for chart-type classification and image generation. We validate the proposed novel network by using it in three different models. The first use case is a traditional SCNN classifier where the model achieves average classification accuracy of 97.14%. The second use case consists of two previously introduced SCNN-based models in parallel, with the same configuration, shared weights, and parameters mirrored and updated in both models. The model achieves average classification accuracy of 100%. The third proposed use case consists of two distinct models, a generator and a discriminator, which are both trained simultaneously using an adversarial process. The generated chart images are plausible to the originals. Extensive experimental analysis end evaluation is provided for the classification task of seven chart classes. The results show that the proposed SCNN is a powerful tool for chart image classification and generation, comparable with Deep Convolutional Neural Networks (DCNNs) but with higher efficiency, reduced computational time, and space complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Multi-Purpose Shallow Convolutional Neural Network for Chart Images

Bajić

Orel

Habijan

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Over the years, authors used different key approaches to achieve the highest average classification accuracy. These approaches can be grouped into four categories: custom algorithm [ 5 , 6 , 7 , 8 ], model-based approach [ 9 , 10 , 11 ], Support Vector Machines [ 2 , 12 , 13 ], and neural networks [ 14 , 15 , 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

Data Extraction of Circular-Shaped and Grid-like Chart Images

Bajić

Job

2022

J. Imaging

View full text Add to dashboard Cite

Chart data extraction is a crucial research field in recovering information from chart images. With the recent rise in image processing and computer vision algorithms, researchers presented various approaches to tackle this problem. Nevertheless, most of them use different datasets, often not publicly available to the research community. Therefore, the main focus of this research was to create a chart data extraction algorithm for circular-shaped and grid-like chart types, which will accelerate research in this field and allow uniform result comparison. A large-scale dataset is provided containing 120,000 chart images organized into 20 categories, with corresponding ground truth for each image. Through the undertaken extensive research and to the best of our knowledge, no other author reports the chart data extraction of the sunburst diagrams, heatmaps, and waffle charts. In this research, a new, fully automatic low-level algorithm is also presented that uses a raster image as input and generates an object-oriented structure of the chart of that image. The main novelty of the proposed approach is in chart processing on binary images instead of commonly used pixel counting techniques. The experiments were performed with a synthetic dataset and with real-world chart images. The obtained results demonstrate two things: First, a low-level bottom-up approach can be shared among different chart types. Second, the proposed algorithm achieves superior results on a synthetic dataset. The achieved average data extraction accuracy on the synthetic dataset can be considered state-of-the-art within multiple error rate groups.

show abstract

Review of chart image detection and classification

Bajić

Job

2023

IJDAR

View full text Add to dashboard Cite

ChartFuse: a novel fusion method for chart classification using heterogeneous microstructures

Cited by 8 publications

References 40 publications

A Multi-Purpose Shallow Convolutional Neural Network for Chart Images

A Multi-Purpose Shallow Convolutional Neural Network for Chart Images

Data Extraction of Circular-Shaped and Grid-like Chart Images

Review of chart image detection and classification

Contact Info

Product

Resources

About