DBDH: A Dual-Branch Dual-Head Neural Network for Invisible Embedded Regions Localization

TL;DR

This paper introduces DBDH, a dual-branch neural network designed to accurately localize invisible embedded regions in images by capturing high-frequency signals and discriminative features, improving decoding accuracy.

Contribution

The paper proposes a novel dual-branch neural network with specialized heads for precise localization of invisible embedded regions, addressing limitations of existing methods.

Findings

DBDH outperforms existing localization methods in accuracy.

The segmentation head improves pixel-level localization.

Experiments validate the effectiveness of high-pass filters in high-frequency signal detection.

Abstract

Embedding invisible hyperlinks or hidden codes in images to replace QR codes has become a hot topic recently. This technology requires first localizing the embedded region in the captured photos before decoding. Existing methods that train models to find the invisible embedded region struggle to obtain accurate localization results, leading to degraded decoding accuracy. This limitation is primarily because the CNN network is sensitive to low-frequency signals, while the embedded signal is typically in the high-frequency form. Based on this, this paper proposes a Dual-Branch Dual-Head (DBDH) neural network tailored for the precise localization of invisible embedded regions. Specifically, DBDH uses a low-level texture branch containing 62 high-pass filters to capture the high-frequency signals induced by embedding. A high-level context branch is used to extract discriminative features between the embedded and normal regions. DBDH employs a detection head to directly detect the four vertices of the embedding region. In addition, we introduce an extra segmentation head to segment the mask of the embedding region during training. The segmentation head provides pixel-level supervision for model learning, facilitating better learning of the embedded signals. Based on two state-of-the-art invisible offline-to-online messaging methods, we construct two datasets and augmentation strategies for training and testing localization models. Extensive experiments demonstrate the superior performance of the proposed DBDH over existing methods.