Text Detection on Roughly Placed Books by Leveraging a Learning-based Model Trained with Another Domain Data

TL;DR

This paper presents algorithms that leverage existing learning-based text detection models trained on different domains to accurately generate bounding boxes for text in roughly placed books, enabling effective automatic text detection without extensive domain-specific training.

Contribution

The paper introduces algorithms that improve and leverage pre-trained models for text detection on books with rough placement, reducing the need for domain-specific training data.

Findings

Algorithms work well in various rough placement scenarios

Leverages models trained on different domains effectively

Enables automatic text detection without extensive new training

Abstract

Text detection enables us to extract rich information from images. In this paper, we focus on how to generate bounding boxes that are appropriate to grasp text areas on books to help implement automatic text detection. We attempt not to improve a learning-based model by training it with an enough amount of data in the target domain but to leverage it, which has been already trained with another domain data. We develop algorithms that construct the bounding boxes by improving and leveraging the results of a learning-based method. Our algorithms can utilize different learning-based approaches to detect scene texts. Experimental evaluations demonstrate that our algorithms work well in various situations where books are roughly placed.