Evaluating the robustness of image matting algorithm

CAAI Transactions on Intelligence Technology

Hui Fan¹  Jinjiang Li¹  Genji Yuan¹ 

[1] School of Computer Science and Technology, Shandong Technology and Business University;

关键词: feature extraction;    gaussian processes;    image texture;    image denoising;    image restoration;    image matting algorithm;    alpha masking;    consistent alpha masks;    gaussian–hermite moment;    gradient amplitude;    gradient direction;    texture changes;    gaussian blur;    pretzel noise;    noise alpha mask;    evaluation levels;    noise level;    noisy images;    trap matting algorithm;   

DOI  :  10.1049/trit.2020.0079

来源: DOAJ

【 摘 要 】

In this study, the authors propose a method to calculate the consistency of alpha masking to assess the robustness of the matting algorithm. This study evaluates consistent alpha masks based on the Gaussian–Hermite moment in combination with gradient amplitude and gradient direction. The gradient direction describes the appearance and shape of local objects in the image, and the gradient amplitude accurately reflects the contrast and texture changes of small details in the image. They selected Gaussian blur, pretzel noise, and combined noise to destroy the image, and then evaluated the consistency of the original alpha mask and noise alpha mask. To determine the robustness of the matting algorithm, they assessed the degree of consistency of the alpha mask using three different evaluation levels. The experimental results show that noise has a greater impact on the performance of the matting algorithm, which shows a decreasing trend as the noise level in the image deepens. In noisy images, the traditional matting algorithm exhibits better robustness compared to the recently proposed trap matting algorithm. Different matting algorithms present different adaptations to different noises.

【 授权许可】

Unknown