Text-Aware Single Image Specular Highlight Removal

TL;DR

This paper introduces a novel approach for removing specular highlights from images containing text, aiming to improve text detection and recognition accuracy by developing a specialized two-stage network and providing high-quality datasets.

Contribution

The paper presents the first text-aware specular highlight removal method with a two-stage network and releases new datasets to advance research in this area.

Findings

Outperforms existing highlight removal methods on text images

Improves text detection and recognition accuracy

Provides high-quality annotated datasets

Abstract

Removing undesirable specular highlight from a single input image is of crucial importance to many computer vision and graphics tasks. Existing methods typically remove specular highlight for medical images and specific-object images, however, they cannot handle the images with text. In addition, the impact of specular highlight on text recognition is rarely studied by text detection and recognition community. Therefore, in this paper, we first raise and study the text-aware single image specular highlight removal problem. The core goal is to improve the accuracy of text detection and recognition by removing the highlight from text images. To tackle this challenging problem, we first collect three high-quality datasets with fine-grained annotations, which will be appropriately released to facilitate the relevant research. Then, we design a novel two-stage network, which contains a highlight detection network and a highlight removal network. The output of highlight detection network provides additional information about highlight regions to guide the subsequent highlight removal network. Moreover, we suggest a measurement set including the end-to-end text detection and recognition evaluation and auxiliary visual quality evaluation. Extensive experiments on our collected datasets demonstrate the superior performance of the proposed method.