Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images
This addresses the challenge of line chart data extraction from camera images for applications in document digitization and data analysis, representing an incremental improvement over existing methods focused on clean images.
The paper tackles the problem of extracting numerical data from line chart images taken by cameras, proposing a synthetic data generation framework and a one-stage model that outputs text labels, mark coordinates, and perspective estimation simultaneously, achieving results applicable to real photos without fine-tuning.
Line Chart Data Extraction is a natural extension of Optical Character Recognition where the objective is to recover the underlying numerical information a chart image represents. Some recent works such as ChartOCR approach this problem using multi-stage networks combining OCR models with object detection frameworks. However, most of the existing datasets and models are based on "clean" images such as screenshots that drastically differ from camera photos. In addition, creating domain-specific new datasets requires extensive labeling which can be time-consuming. Our main contributions are as follows: we propose a synthetic data generation framework and a one-stage model that outputs text labels, mark coordinates, and perspective estimation simultaneously. We collected two datasets consisting of real camera photos for evaluation. Results show that our model trained only on synthetic data can be applied to real photos without any fine-tuning and is feasible for real-world application.