Object contour plays an important role in fields such as semantic segmentation and image classification. However, the extraction of contour is a difficult task, especially when the contour is incomplete or unclosed. I...Object contour plays an important role in fields such as semantic segmentation and image classification. However, the extraction of contour is a difficult task, especially when the contour is incomplete or unclosed. In this paper, the existing contour detection approaches are reviewed and roughly divided into three categories： pixel-based, edge-based, and region-based. In addition, since the traditional contour detection approaches have achieved a high degree of sophistication, the deep convolutional neural networks （DCNNs） have good performance in image recognition, therefore, the DCNNs based contour detection approaches are also covered in this paper. Moreover, the future development of contour detection is analyzed and predicted.展开更多
提出了一种基于轮廓线统计量的前景分割Markov随机场(Markov random field,MRF)模型,和Grabcut等以往模型不同,本文模型通过在分割标签的编码中加入对轮廓线方向的考虑,将Gestalt知觉组织的原则加入分割约束中去,从而使分割边界更为平滑...提出了一种基于轮廓线统计量的前景分割Markov随机场(Markov random field,MRF)模型,和Grabcut等以往模型不同,本文模型通过在分割标签的编码中加入对轮廓线方向的考虑,将Gestalt知觉组织的原则加入分割约束中去,从而使分割边界更为平滑,作为前景分割和Gestalt知觉组织原则研究的基本框架,本文模型的系统结构分为前景分割、注意力选择和信息整合三个子模块,与相关神经生理研究的结论相一致,最后,分别给出了基于本文模型的自动和半自动前景分割实现,结果好于Grabcut等相关算法的结果。展开更多
基金supported by National Natural Science Foundation of China (Nos. 61503378, 61473293, 51405485 and 61403378)the Project of Development in Tianjin for Scientific Research Institutes, and Tianjin Government (No. 16PTYJGX00050)
文摘Object contour plays an important role in fields such as semantic segmentation and image classification. However, the extraction of contour is a difficult task, especially when the contour is incomplete or unclosed. In this paper, the existing contour detection approaches are reviewed and roughly divided into three categories： pixel-based, edge-based, and region-based. In addition, since the traditional contour detection approaches have achieved a high degree of sophistication, the deep convolutional neural networks （DCNNs） have good performance in image recognition, therefore, the DCNNs based contour detection approaches are also covered in this paper. Moreover, the future development of contour detection is analyzed and predicted.
文摘提出了一种基于轮廓线统计量的前景分割Markov随机场(Markov random field,MRF)模型,和Grabcut等以往模型不同,本文模型通过在分割标签的编码中加入对轮廓线方向的考虑,将Gestalt知觉组织的原则加入分割约束中去,从而使分割边界更为平滑,作为前景分割和Gestalt知觉组织原则研究的基本框架,本文模型的系统结构分为前景分割、注意力选择和信息整合三个子模块,与相关神经生理研究的结论相一致,最后,分别给出了基于本文模型的自动和半自动前景分割实现,结果好于Grabcut等相关算法的结果。
