Doing More With Moiré Pattern Detection in Digital Photos

Abstract

Detecting moiré patterns in digital photographs is meaningful as it provides priors towards image quality evaluation and demoiréing tasks. In this paper, we present a simple yet efficient framework to extract moiré edge maps from images with moiré patterns. The framework includes a strategy for training triplet (natural image, moiré layer, and their synthetic mixture) generation, and a Moiré Pattern Detection Neural Network (MoireDet) for moiré edge map estimation. This strategy ensures consistent pixel-level alignments during training, accommodating characteristics of a diverse set of camera-captured screen images and real-world moiré patterns from natural images. The design of three encoders in MoireDet exploits both high-level contextual and low-level structural features of various moiré patterns. Through comprehensive experiments, we demonstrate the advantages of MoireDet: better identification precision of moiré images on two datasets, and a marked improvement over state-of-the-art demoiréing methods.

Securing Phygital Gameplay: Strategies for Video-Replay Spoofing Detection

“…These results align with Yang et al's observations [48], emphasizing Moiré pattern sensitivity to scales and resolutions. Our generalization study outcomes reinforce the value of our dataset, affirming its capacity to effectively train our model in acquiring meaningful detection features.…”

“…Our experimentation methodology involved applying the model trained on the sqiller-spoof dataset to these distinct datasets for the purpose of generalization analysis. Notably, it is highlighted by Yang et al [48] that Moiré patterns lack resilience when confronted with background variations and furthermore, visual dissimilarities exist between perceptually varying settings such as phygital games and facial biometric recognition contexts. The majority of facial biometric spoof datasets encompass not only video replay attacks, but also encompass a range of other attack modalities, including 2D photo attacks, paper masking attacks, and 3D rigid silicone mask attacks.…”

Screen recapture detection based on color-texture analysis of document boundary regions

“…where T c ,  t ,  c are configurable thresholds. When analyzing a color texture, the parameters are independently verified in each channel, and finally, the texture is considered "leaking" if the condition (7) is met for at least two of the three channels.…”