Abstract:The textual data of a document is supplemented by the graphical information in it. To make communication easier, they contain tables, charts and images. However, it excludes a section of our population -the visually impaired. With technological advancements, the blind can access the documents through text to speech software solutions. In this method, even images can be conveyed by reading out the figure captions. However, charts and other statistical comparisons which involve critical information are difficult… Show more
“…The paper [19] review the traditional methods and recent trends in the accessibility of visualization data and the potential future of artificial intelligence in reverse-engineering the chart data. The work, Revision [1] extracts low-level image features and classifies them using machine learning approach with 80% accuracy.…”
Graphical representations such as chart images are integral to web pages and documents. Automating data extraction from charts is possible by reverse-engineering the visualization pipeline. This study proposes a framework that automates data extraction from bar charts and integrates it with questionanswering. The framework employs an object detector to recognize visual cues in the image, followed by text recognition. Mask-RCNN for plot element detection achieves a mean average precision of 95.04% at a threshold of 0.5 which decreases as the Intersection over Union (IoU) threshold increases. A contour approximation-based approach is proposed for extracting the bar coordinates, even at a higher IoU of 0.9. The textual and visual cues are associated with the legend text and preview, and the chart data is finally extracted in tabular format. We introduce an extension to the TAPAS model, called TAPAS++, by incorporating new operations and table question answering is done using TAPAS++ model. The chart summary or description is also produced in an audio format. In the future, this approach could be expanded to enable interactive question answering on charts by accepting audio inquiries from individuals with visual impairments and do more complex reasoning using Large Language Models.
“…The paper [19] review the traditional methods and recent trends in the accessibility of visualization data and the potential future of artificial intelligence in reverse-engineering the chart data. The work, Revision [1] extracts low-level image features and classifies them using machine learning approach with 80% accuracy.…”
Graphical representations such as chart images are integral to web pages and documents. Automating data extraction from charts is possible by reverse-engineering the visualization pipeline. This study proposes a framework that automates data extraction from bar charts and integrates it with questionanswering. The framework employs an object detector to recognize visual cues in the image, followed by text recognition. Mask-RCNN for plot element detection achieves a mean average precision of 95.04% at a threshold of 0.5 which decreases as the Intersection over Union (IoU) threshold increases. A contour approximation-based approach is proposed for extracting the bar coordinates, even at a higher IoU of 0.9. The textual and visual cues are associated with the legend text and preview, and the chart data is finally extracted in tabular format. We introduce an extension to the TAPAS model, called TAPAS++, by incorporating new operations and table question answering is done using TAPAS++ model. The chart summary or description is also produced in an audio format. In the future, this approach could be expanded to enable interactive question answering on charts by accepting audio inquiries from individuals with visual impairments and do more complex reasoning using Large Language Models.
“…In [1], This paper presents a method for defining the area of interest (ROI) in which objects can be segregated from messy backgrounds that is both efficient and effective. To obtain text information, this ROI extracts the text localization and recognition.…”
Often, language bias between communicators can create communication problems. This article discusses a prototype that addresses this issue by enabling users to hear the content of text images. This involves extracting the text from the image and converting it into speech in the user's preferred language. Additionally, the device can be used by people with visual impairments. Overall, this device helps users to listen to the content of images being presented. The suggested system allows the user to take a picture, which is then scanned and analysed by the application to read the English text. The information obtained is then converted into voice, enabling visually impaired individuals to understand the content of the text. The output is delivered in speech format to provide access to information present on the document. To ensure better accuracy and performance, the system uses Natural Language Processing techniques. The system is designed with a Graphical User Interface (GUI) to improve accuracy and ease of use.
“…For example, people with impaired vision and all blind individuals can not access the “locked” information inside chart images. These people often rely on assistive technology (braille display, screen readers, and speech converters), which can only read the information that is provided by the author in the surrounding text [ 3 , 4 ]. Manual reading of chart images is often inaccurate and can not be used for scientific purposes.…”
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.