Advances in Multimedia最新文献

Images Inpainting Quality Evaluation Using Structural Features and Visual Saliency 利用结构特征和视觉显著性进行图像绘制质量评估

IF 1.4 Q4 Computer Science

Advances in Multimedia

Pub Date : 2024-05-14 DOI: 10.1155/2024/5066916

Shuang Ma, Jinhe Liu

Despite the extensive research on developing robust image inpainting algorithms in recent years, there are almost no objective metrics for the quality assessment of inpainted images currently. Inspired by the feature coherence in the inpainted image and the human visual perception mechanism, this paper proposes an image inpainting quality assessment (IIQA) that takes into account both visual saliency and structural features. First, the quality issues associated with image inpainting are categorized into three aspects: incoherent structure, unreasonable texture, and other results that are inconsistent with human visual perception. These quality problems are further expressed as “regions of interest” and extracted by the visual saliency method using the natural statistics model. Subsequently, the structural features are computed based on the nonlinear diffusion of the horizontal and vertical gradient field of the inpainted image. Finally, the IIQA metric incorporates brightness, gradient similarity, structural similarity, and visual saliency is established. The quality evaluation process is conducted by comparing each patch within the inpainted region with its best match from the known region. The quantitative experimental results demonstrate the effectiveness of the proposed method, especially for images with structural discontinuity. A comparative study also shows that the Spearman rank order correlation coefficient of our method achieves 0.875 on certain databases, which outperforms existing IIQA metrics.

尽管近年来人们对开发鲁棒图像内绘算法进行了广泛的研究，但目前几乎没有客观的指标来评估内绘图像的质量。受内绘图像特征一致性和人类视觉感知机制的启发，本文提出了一种同时考虑视觉显著性和结构特征的图像内绘质量评估（IIQA）。首先，将与图像内绘相关的质量问题分为三个方面：结构不连贯、纹理不合理以及其他与人类视觉感知不一致的结果。这些质量问题被进一步表述为 "感兴趣区域"，并通过视觉显著性方法利用自然统计模型进行提取。随后，根据涂色图像水平和垂直梯度场的非线性扩散计算结构特征。最后，建立了包含亮度、梯度相似性、结构相似性和视觉显著性的 IIQA 指标。质量评估过程是通过将内绘区域内的每个补丁与已知区域内的最佳匹配补丁进行比较。定量实验结果证明了所提方法的有效性，尤其是对于结构不连续的图像。对比研究还表明，我们的方法在某些数据库中的斯皮尔曼秩相关系数达到了 0.875，优于现有的 IIQA 指标。

{"title":"Images Inpainting Quality Evaluation Using Structural Features and Visual Saliency","authors":"Shuang Ma, Jinhe Liu","doi":"10.1155/2024/5066916","DOIUrl":"https://doi.org/10.1155/2024/5066916","url":null,"abstract":"Despite the extensive research on developing robust image inpainting algorithms in recent years, there are almost no objective metrics for the quality assessment of inpainted images currently. Inspired by the feature coherence in the inpainted image and the human visual perception mechanism, this paper proposes an image inpainting quality assessment (IIQA) that takes into account both visual saliency and structural features. First, the quality issues associated with image inpainting are categorized into three aspects: incoherent structure, unreasonable texture, and other results that are inconsistent with human visual perception. These quality problems are further expressed as “regions of interest” and extracted by the visual saliency method using the natural statistics model. Subsequently, the structural features are computed based on the nonlinear diffusion of the horizontal and vertical gradient field of the inpainted image. Finally, the IIQA metric incorporates brightness, gradient similarity, structural similarity, and visual saliency is established. The quality evaluation process is conducted by comparing each patch within the inpainted region with its best match from the known region. The quantitative experimental results demonstrate the effectiveness of the proposed method, especially for images with structural discontinuity. A comparative study also shows that the Spearman rank order correlation coefficient of our method achieves 0.875 on certain databases, which outperforms existing IIQA metrics.","PeriodicalId":44067,"journal":{"name":"Advances in Multimedia","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140978572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}