Segregating and extracting overlapping data points in two-dimensional plots

Browuer, William; Kataria, Saurabh; Das, Sujatha; Mitra, Prasenjit; Giles, C. Lee

doi:10.1145/1378889.1378936

Cited by 15 publications

(10 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the linear kernel SVM with ten principal components was trained on the entire training data, and the evaluation results for test data are reported in 2. As can be seen, the test accuracy is 0.85, which is comparable to a similar work by Browuer et al [1]. Positive Negative Total Predicted Classes Positive 25 6 31 Negative 2 21 23 Total 27 27 54 Table 2: Confusion matrix on test data.…”

Section: Experiments and Resultssupporting

confidence: 80%

See 1 more Smart Citation

An Architecture for Information Extraction from Figures in Digital Libraries

Choudhury

Giles

2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

Scholarly documents contain multiple figures representing experimental findings. These figures are generated from data which is not reported anywhere else in the paper. We propose a modular architecture for analyzing such figures. Our architecture consists of the following modules: 1. An extractor for figures and associated metadata (figure captions and mentions) from PDF documents; 2. A Search engine on the extracted figures and metadata; 3. An image processing module for automated data extraction from the figures and 4. A natural language processing module to understand the semantics of the figure. We discuss the challenges in each step, report an extractor algorithm to extract vector graphics from scholarly documents and a classification algorithm for figures. Our extractor algorithm improves the state of the art by more than 10% and the classification process is very scalable, yet achieves 85% accuracy. We also describe a semi-automatic system for data extraction from figures which is integrated with our search engine to improve user experience.

show abstract

Section: Experiments and Resultssupporting

confidence: 80%

“…Some previous works focused on 2D/non 2D plot binary classification [1] and some addressed multi class classification (line graph, bar graph, scatter plot etc) [12]. A recent work by Savva et al [12] showed that unsupervised feature learning can produce better results than complicated feature engineering [11].…”

Section: Related Workmentioning

confidence: 99%

An Architecture for Information Extraction from Figures in Digital Libraries

Choudhury

Giles

2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

show abstract

“…The problem of understanding statistical charts has been previously studied in the literature [6], [7], [8], [9] for tasks which often focus on chart detection [10], [11], chart classification [12], [13], detection and recognition of textual components [14], [15] and information extraction from charts [13], [15]. We found that mostly computer-vision based techniques have been used to extract visual elements from the bar charts.…”

Section: Related Workmentioning

confidence: 99%

ChartNet: Visual Reasoning over Statistical Charts using MAC-Networks

Sharma¹,

Chowdhury²,

Vig³

2019

2019 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Despite the improvements in perception accuracies brought about via deep learning, developing systems combining accurate visual perception with the ability to reason over the visual percepts remains extremely challenging. A particular application area of interest from an accessibility perspective is that of reasoning over statistical charts such as bar and pie charts. To this end, we formulate the problem of reasoning over statistical charts as a classification task using MAC-Networks to give answers from a predefined vocabulary of generic answers. Additionally, we enhance the capabilities of MAC-Networks to give chart-specific answers to open-ended questions by replacing the classification layer by a regression layer to localize the textual answers present over the images. We call our network ChartNet, and demonstrate its efficacy on predicting both in vocabulary and out of vocabulary answers. To test our methods, we generated our own dataset of statistical chart images and corresponding question answer pairs. Results show that ChartNet consistently outperform other state-of-the-art methods on reasoning over these questions and may be a viable candidate for applications containing images of statistical charts.

show abstract

“…Browuer et al and Kataria et al describe a method of detecting plots by means of wavelet analysis. 9,10 They focus on the extraction of data points from identified figures. In particular, they address the challenge of correctly identifying overlapping points of data in plots.…”

Section: Related Workmentioning

confidence: 99%