A Distraction Score for Watermarks
This addresses the need for automated assessment of watermark distraction in image processing, particularly for ranking applications, but appears incremental as it builds on existing detection methods.
The paper tackles the problem of quantifying how distracting watermarks are on images by proposing a technique that uses a two-tower CNN model for detection and a nonlinear function to generate a single score based on size, location, and obstructiveness, validated in an image ranking setup.
In this work we propose a novel technique to quantify how distracting watermarks are on an image. We begin with watermark detection using a two-tower CNN model composed of a binary classification task and a semantic segmentation prediction. With this model, we demonstrate significant improvement in image precision while maintaining per-pixel accuracy, especially for our real-world dataset with sparse positive examples. We fit a nonlinear function to represent detected watermarks by a single score correlated with human perception based on their size, location, and visual obstructiveness. Finally, we validate our method in an image ranking setup, which is the main application of our watermark scoring algorithm.