Table De- tection using Attention-based Networks

Abstract

Table detection is a fundamental step in many document image analysis systems. It is a challenging problem due to variety of table layouts, encoding techniques and the similarity of tabular regions with non-tabular document elements. Earlier approaches of table detection are based on heuristic rules or require additional PDF metadata. Recently proposed methods based on machine learning have shown good results. This paper, based on foreground features, describes performance improvement to these table detection techniques. Proposed solution is based on the observation that tables tend to contain more numeric data and hence it applies color coding/coloration as a signal for telling apart numeric and textual information. Deep learning based Faster R-CNN is used for detection of tabular regions from document images. To gauge the performance of our proposed solution, publically available UNLV dataset is used. Performance measures indicate improvement when compared with best in-class strategies.