Chart-RCNN: Efficient Line Chart Data Extraction from Camera Images

TL;DR

This paper introduces Chart-RCNN, a one-stage model trained on synthetic data for extracting data from line charts in camera images, demonstrating effective real-world application without fine-tuning.

Contribution

Proposes a synthetic data generation framework and a one-stage model for line chart data extraction from camera images, reducing reliance on extensive labeled datasets.

Findings

Model trained on synthetic data performs well on real camera photos.

The approach eliminates the need for fine-tuning on real data.

Two real-world datasets were collected for evaluation.

Abstract

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.