纺织学报 ›› 2018, Vol. 39 ›› Issue (03): 126-131.doi: 10.13475/j.fzxb.20161001406

• 服装工程 • 上一篇    下一篇

服饰设计视觉显著性检测

  

  • 收稿日期:2016-10-09 修回日期:2017-12-12 出版日期:2018-03-15 发布日期:2018-03-09

Visual saliency detection of clothing and accessory design

  • Received:2016-10-09 Revised:2017-12-12 Online:2018-03-15 Published:2018-03-09

摘要:

为快速、批量化检测服饰品的视觉兴趣度,依据人眼视觉注意模型,利用自底向上的视觉显著性检测方法描述服饰图像的视觉显著性。提取服饰图像的亮度、色彩、纹理方向 3 个底层特征,利用多尺度的分解方法构建出图像的多特征通道;采用归一化合并的方式对特征显著图进行滤波;对形成的 3 类特征图进行融合,根据显著程度绘制视觉热点图及亮度图,从而划分图像的视觉显著区域,并进一步提出了视觉覆盖率和分散度 2 个指标,用以对服饰图像的视觉显著性差异进行量化和评价。对常见色块、不同纹理织物、服装及配饰图视觉显著度进行实验检测,结果表明,本文方法可有效地描绘出图像视觉显著区域,快速、客观地评定出服饰图像的视觉显著度。

关键词: 服饰设计, 视觉显著性, 热点图, 客观评介

Abstract:

In order to fastly and batch detect the visual interestingness of clothing and accessory images, the bottom-to-top visual saliency detection method was utilized to describe the visual saliency based on human visual attention model. Firstly, the bottom characteristics including brightness, color and texture of fashion image were extracted to construct multiple feature channels. Besides, combining normalized method was used to filter the feature image. Finally, the constructed three feature maps were fused and the visual focus area and significant bright map layer were converged. In the experiment, the visual saliency of color blocks map, different texture fabric images, clothing and accessory image were detected. The results show that the proposed algorithm effectively and objectively extracts the salient region and presents the significant degree.

Key words: fashion and accessory design, visual saliency, hot map, objective evaluation

[1] 李学伟. 鲁锦的创意再设计[J]. 纺织学报, 2017, 38(06): 58-63.
[2] 李敏 崔树芹 陈佳. 应用视觉显著性的小提花织物疵点检测[J]. 纺织学报, 2016, 37(12): 38-42.
[3] 管声启 高照元 吴宁 徐帅华. 基于视觉显著性的平纹织物疵点检测[J]. 纺织学报, 2014, 35(4): 56-0.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!