Bounding box guidance improves table structure recognition accuracy
Enhancing Table Structure Recognition via Bounding Box Guidance
Computer Vision and Pattern Recognition
Summary
Recognizing tables in images means figuring out where each cell is and how they fit together. The authors noticed that many current methods miss using the exact locations of table cells when turning an image into a code-like description. They propose a new method that first finds the locations of cells and then uses this to better predict the table’s structure. To train and test this method especially on photos of tables in natural scenes, they created a synthetic dataset. Their approach showed improved accuracy across several tests.
What this means in practice
- •For document processing teams: Improve automatic extraction of table layouts from scanned and photographed documents using precise cell location guidance.
- •For data entry automation providers: Enhance extraction accuracy from complex natural scene images of tables, enabling better automated data digitization services.$Commercial implications: This method enables better automated table extraction products for clients needing accurate data capture from varied image sources.
Authors
Lei Hu, Shuangping Huang
Abstract
Table Structure Recognition (TSR) aims to extract the bounding boxes of cells and table structure (e.g., HTML) from table images. Although current approaches have made significant progress, the latest image-to-sequence methods overlook the explicit utilization of the bounding box information when predicting HTML sequences, leading to error predictions in complex scenes. In this paper, we introduce a novel framework BGTR (Bounding Box-Guided Table Recognizer). To more effectively utilize bounding box information, we first predict the bounding boxes of cells and then use this information to guide the generation of HTML sequences. While utilizing bounding box information can enhance the accuracy of HTML sequences, for natural scene tables, the data volume is too small to allow for sufficient training of bbox-guided HTML generation. In response, we adopt a progressive training method for natural scene tables and introduce SNSTab, a synthetically generated natural scene table dataset. Our experiments on five benchmark datasets demonstrate SOTA performance.