In recovering information from the chart image, the first step should be chart type classification. Throughout history, many approaches have been used, and some of them achieve results better than others. The latest articles are using a Support Vector Machine (SVM) in combination with a Convolutional Neural Network (CNN), which achieve almost perfect results with the datasets of few thousand images per class. The datasets containing chart images are primarily synthetic and lack real-world examples. To overcome the problem of small datasets, to our knowledge, this is the first report of using Siamese CNN architecture for chart type classification. Multiple network architectures are tested, and the results of different dataset sizes are compared. The network verification is conducted using Few-shot learning (FSL). Many of described advantages of Siamese CNNs are shown in examples. In the end, we show that the Siamese CNN can work with one image per class, and a 100% average classification accuracy is achieved with 50 images per class, where the CNN achieves only average classification accuracy of 43% for the same dataset.

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.

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.

We introduce a meticulously curated synthetic chart dataset designed to propel algorithm advancements in data visualization and interpretation. The dataset, tailored for training and testing purposes, encompasses a diverse array of chart types, including but not limited to Area, Bar, Box, Donut, Line, Pie, and Scatter. The data collection process involves a fully automatic low-level algorithm focused on extraction of graphical elements. The algorithm ensures efficiency by restricting input images from featuring three-dimensional representations, incorporating any 3D effects, or including multiple charts in a single image. The dataset is categorized into training and testing subsets, further subdivided based on resolutions and specific chart types. The reuse potential of this dataset is substantial. It serves as a valuable resource for driving algorithmic advancements in data visualization classification and interpretation. Researchers can leverage this dataset for training and testing deep models, enhancing the adaptability of their algorithms. Moreover, it establishes a benchmark for evaluating system performance in handling diverse chart visualizations, allowing for direct comparisons, and fostering advancements in data understanding algorithms. The versatility of the dataset, encapsulating various chart types and resolutions, provides a standardized platform for assessing and comparing the effectiveness of different systems in understanding and decomposing visualizations [1,2,3].

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.